This policy is designed to provide guidance to developers building Actions on Google that will be published in the Directory. Some partners may have access to additional APIs and be subject to varying policies.
This policy applies to Actions in their entirety, including in-Action content, advertising content (where permitted), Action behaviour, and Action listings in the Directory.
We don't allow Actions that facilitate or promote sexual gratification or sexually explicit content. This includes:
- Pornographic, sexually explicit, or erotic content.
- Content that describes sexual acts or sex toys.
- Escort services or other services that may be interpreted as providing sexual acts in exchange for compensation.
- Content that describes or encourages bestiality.
Google has a zero-tolerance policy against child sexual abuse content. If we become aware of content facilitating or promoting the distribution of child sexual abuse content, we will report it to the appropriate authorities and delete the Google Accounts of those involved with the distribution.
Violence and dangerous activities
We don't allow Actions that facilitate or promote gratuitous violence or dangerous activities. This includes:
- Graphic descriptions of realistic violence or violent threats to any person or animal.
- Terrorist groups documenting their attacks.
- Instructions for engaging in or facilitating violent activities, including bomb-making or weapon-making.
- Self-harm, including instructions to carry out self-harm.
Bullying and harassment
We don't allow Actions that facilitate threats, harassment, or bullying. This includes content primarily intended to harass or single out another person for abuse, malicious attack, or ridicule.
We don't allow Actions that facilitate or promote content that advocates hate or violence against groups of people based on their race or ethnic origin, religion, disability, gender, age, nationality, veteran status, sexual orientation, or gender identity.
Actions that facilitate or promote near-hate negativity towards a protected group are prohibited. This includes Actions that make inflammatory or excessively negative statements about:
- Appearance or hygiene.
- Socio-economic status.
- Ethics or morality.
- Disability or medical condition.
- Criminal history.
- Sexual activity.
We don't allow Actions that lack reasonable sensitivity towards, or capitalize on, a natural disaster, atrocity, conflict, death, or other tragic event.
We don't allow Actions that facilitate or promote online gambling services, including but not limited to, online casinos, sports betting, lotteries, or games of skill regardless of whether they offer prizes of cash or other value.
We don't allow Actions that facilitate or promote illegal activities. This includes:
- Use, sale, or purchase of illegal drugs or prescription drugs without a prescription.
- Use or sale of alcohol or tobacco by minors.
- Instructions for growing or manufacturing illegal drugs.
You are solely responsible for determining the legality of your Action in its targeted locale. Actions determined to be unlawful in locations where they are published will be removed.
We don't allow Actions that:
- Are, represent themselves as, or provide services as, a health care provider, a health plan, or a health care clearinghouse. Health care providers, health plans or health care clearinghouses wishing to develop an Action should be aware that Google is not able to commit that the Actions on Google platform meets the requirements of HIPAA or other relevant legal provisions.
- Provide health information without also providing a disclaimer in the Directory listing that adequately discloses to the user, in a manner reasonable to the user experience, that such information is not a substitute for advice from a medical professional.
Actions providing fitness functionality, including activity monitoring (calories burned, steps taken, etc.), weight data, and BMI are permitted.
We currently require certain Actions that support in-dialogue operations (such as the buying or selling of virtual or physical goods or services for money or points, making reservations, or booking appointments) to use an API that is currently available in an Early Access Program.
Developers interested in joining this Early Access Program should contact Google.
Intellectual Property, Deception, and Spam
We don't allow Actions or developer accounts that infringe the intellectual property rights of others, including trademark, copyright, patent, trade secret, and other proprietary rights. We also don't allow Actions that encourage or induce infringement of intellectual property rights.
We will respond to clear notices of alleged copyright infringement. For more information or to file a Digital Millennium Copyright Act request, please visit our copyright procedures.
If you are a trademark owner and you believe an Action is infringing on your trademark rights, we encourage you to reach out to the developer directly to resolve your concern. If you can't reach a resolution with the developer, please submit a trademark complaint through this form.
We don't allow Actions that use another Action or entity's brand, title, logo, or name in a manner that may result in misleading users. Don't try to imply an endorsement or relationship with another entity where none exists. Impersonation can occur even if there isn't an intent to deceive, so please be careful when referencing any brands that do not belong to you. This applies even if that brand doesn't yet have a presence on the Directory.
Encouraging infringement of copyright
We don't allow Actions that induce or encourage copyright infringement. Before you publish your Action, look for ways it may be encouraging copyright infringement and get legal advice if necessary.
We don't allow Actions that infringe on others' trademarks. A trademark is a word, symbol, or combination that identifies the source of a good or service. Once acquired, a trademark gives the owner exclusive rights to the trademark usage with respect to certain goods or services.
Trademark infringement is the improper or unauthorized use of an identical or similar trademark in a way that is likely to cause confusion as to the source of that product. If your Action uses another party's trademarks in a way that is likely to cause confusion, your Action may be removed.
We don't allow Actions that attempt to deceive users. Actions must provide accurate disclosure of their functionality and perform as reasonably expected by the user. Actions must not attempt to mimic system functionality or warnings of any kind. Any changes to device settings must be made with the user's knowledge and consent and be easily reversible by the user.
We don't allow Actions that contain false or misleading information or claims, including in the trigger phrase, description, title, or icon.
Examples of misleading claims include:
- Misrepresenting or not accurately and clearly describing Action functionality, for example:
- An Action that claims to be a food delivery service in its description or invocation, but is actually a ride-sharing service.
- An Action that claims to be a restaurant reservation service, but only contains a restaurant reviews.
- An Action that uses a trigger phrase related to coffee, but is actually a pizza delivery service.
- Misrepresenting the current status or performance on the Directory (e.g. "Editor's Choice," "Number 1 Action").
- Featuring medical or health-related functionality that is misleading or potentially harmful.
- Claiming functionality that is impossible to implement.
- Actions that are improperly categorized.
Unauthorized use or imitation of system functionality
We don't allow Actions that mimic or interfere with system functionality. Examples of prohibited behaviour include:
- Using a voice for your Action that mimics the Google Assistant's voice.
- Mimicking system notifications or warnings.
- Pretending to be Google or another Google Action.
We don't allow Actions that spam users or the Directory in any way. Examples of spammy behavior include:
- Actions that push content to users' mobile devices without the user's permission.
- Actions whose primary purpose is to drive traffic to a website or app.
- Submitting multiple duplicative Actions to the Directory.
Privacy and Security
You must be transparent in how you handle user data (e.g., information provided by a user, collected about a user, and collected about a user's use of the Action or device). This policy establishes the Directory's minimum privacy requirements; you or your Action may need to comply with additional restrictions or procedures if required by an applicable law.
All Actions must:
Handle all user data securely
All transmissions of user data must use modern cryptography, and your Action's interaction with the Actions on Google API must use HTTPs.
Accurately describe the reason for requesting user data via a permission API
You must clearly and accurately disclose the reason for requesting user data via a permission API by using the "context" field in the corresponding method.
In addition to the requirements above, the table below describes requirements for specific activities and data types.
|Activity / Data Type||Requirement|
|Payment and Financial Data
(including credit card and bank account numbers)
|Don't collect payment or financial data via the conversational interface (text or speech).|
|Email Addresses||Don't collect email addresses via the conversational interface (text or speech).|
(including passwords, PINs, and answers to security questions)
|Don't collect authentication data via the conversational interface (text or speech).
After a user's account has been linked, Actions may permit or require users to setup a different PIN or password to limit access via the conversational interface.
You may use the Account Linking API and OAuth 2 to create a link between a Google user and an existing account on your system. Don't use any other method to associate a Google user with an account on your system, including using an association from another Action engaging in account linking. For example, if you offer multiple Actions requiring account linking, each action must independently use the Account Linking API -- using the configuration defined in the respective action package — to associate the Google user with the existing account. Only one OAuth config per action package is permitted.
Don't request any OAuth scope from Google unless the user is signing in to your service using Google Sign-In. Don't encourage users to agree to additional Google OAuth scopes by directing them to a website or app.
Device and network abuse
We don't allow Actions that interfere with, disrupt, damage, or access in an unauthorized manner the user's device or other devices, computers, servers, networks, application programming interfaces (APIs), or services. This includes other Actions, any Google service, and the device's network.
We don't allow Actions that steal data, secretly monitor or harm users or that are otherwise malicious.
All Actions that collect user data must comply with the User data policy and fully disclose their functions.
The following are explicitly prohibited:
- Viruses, trojan horses, malware, spyware, and any other malicious software.
- Promoting or facilitating the distribution or installation of malicious software.
- Introducing or exploiting security vulnerabilities.
- Stealing a user's authentication information (such as usernames or passwords).
- Tricking users into disclosing personal or authentication information.
- Running other Actions without the user's prior consent.
- Secretly collecting device usage.
Actions and their listings on the Directory must not provide any means to activate or access functionality that violate these terms.
Monetization and Ads
No in-conversation ads are permitted.
All Actions must have a unique invocation that will allow users to trigger the Action's functionality.
Invocation names must meet the following requirements:
- The invocation name must comply with the Prohibited Content policies and must not include words that are vulgar, sexually explicit or offensive.
- The invocation name must comply with the policy on Intellectual Property and must not infringe other's intellectual property rights or impersonate other brands.
- One-word invocation names are not allowed, unless the invocation name is unique to your brand or trademark. Instructions to request an exception are below. Don't break up compound words to circumvent this requirement, example using key board instead of keyboard.
- Common or generic invocation names are not allowed, for example, thank you.
- Names of people or places are not allowed unless they also contain other words (for example,bill's horoscope or new york tourism).
- Two-word invocation names are not allowed if one of the words is a definite article (the), indefinite article (a or an) or preposition (for, to, or of). For example, your invocation name should not be a bicycle, an espresso, to amuse or for fun.
- Some words are reserved and cannot be used as invocation names, including launch phrases (such as, Ok Google and Volume Up) and connecting words (such as, to, from, and by). Test your name in the API dashboard to confirm it doesn't use a reserved word. We may exceptions for multi-word invocation names using connecting words; instructions to request an exception are below. Invocation names may only use reserved words in qualifying multi-word combinations. Reserved words include game and app.
- Invocation names must contain only lower-case alphabetic characters, spaces between words, possessive apostrophes (for example, sam's science trivia), or periods used in abbreviations (for example, a. b. c.). Other characters such as numbers must be spelled out, for example, twenty one.
- Invocation names must be easy to pronounce correctly and be phonetically distinct to avoid being misinterpreted as other similar sounding words. Don't use invocation names that are phonetically similar to prohibited words, such as vulgar or offensive terms, even if you spell them differently.
We will consider exceptions to certain naming policies on a case-by-case basis; you can request an exception filling out this form and selecting Invocation Name Whitelist.
Store Listing and Promotion
The Directory is how users discover new Actions. Your Action's listing dramatically affects the Directory's quality, so avoid spammy listings, low quality promotion, and anything that artificially boosts your Action's visibility.
Name and invocation
Your listing must include a English-language display name and sample invocation. The display name and invocation must comply with the Naming policy. Each sample invocation must include the invocation name, for example "Start MyAction."
To avoid confusing users, your display name must be related to the invocation name for your Action. Specifically, the display name and invocation name must not have distinct brands or entities.
The display name and invocation name for your Action must not suggest distinct functionality or distinct scope. For example, if the display name for your Action is "Animal Facts," the invocation name must not be "fun facts," because "fun facts" suggests a broader set of facts beyond just animals.
The description of your Action must accurately describe its functionality and the services or content it provides. Here are a few best practices for writing a description of your Action:
- Provide a clear, succinct description of how your Action can help users, for example, "You can use this Action to do X." Excessive length, detail, or repetition in your Action description can result in a violation of this policy.
- Highlight what's great about your Action. Share interesting and exciting facts about to help users understand what makes your Action special.
- Make sure that your Action's title and description accurately describes its functionality.
- Avoid using excessive, repetitive, or unrelated keywords or references.
- Disclose whether your Action requires payment for any of its features.
User testimonials are not allowed in the Action's description.
We don't allow Actions that directly or indirectly engage in or benefit from promotional practices that are deceptive or harmful to users or the developer ecosystem. This includes Actions that engage in the following behavior:
- Using deceptive ads on websites, apps, or other properties, including notifications that are similar to system notifications and alerts.
- Engaging in unsolicited promotion via SMS services.
- Offering compensation for enabling Actions, including money, digital or physical goods.
It is your responsibility to ensure that any ad networks or affiliates associated with your Action comply with these policies and do not employ any prohibited promotion practices.
Actions targeting children under 13 or providing content explicitly for children under 13 are not allowed at this time.
To ensure a great user experience, your Action must operate as described, provide a high quality user experience, and take advantage of the platform's features.
Actions should follow the guidance for Conversation Design. Actions that significantly deviate from the design guidance may be rejected or removed for having a poor user experience. This includes:
- Suggesting the Action supports a larger scope of commands than it actually does.
- For example, if the Action says "Ask me anything," but the Action can only answer the question "Who is president of the United States?".
- Listening for a user command without prompting the user.
- For example, if the Action answers a user's question and then starts to listen for an additional command without any prompt to the user suggesting a command or asking question.
- Playing a silent sound file.
- Your Action's query patterns must be relevant enough so that users wouldn't be surprised if your Action was recommended or invoked.
In addition, we reserve the right to reject Actions on the basis of content or functionality that are not explicitly prohibited by these policies, but that run contrary to these policies in spirit. In the event that your Action is rejected or removed under this section, we pledge provide an explanation of our decision.
These policies do not limit or amend any terms of service or other agreements that apply to the user's use of the applicable Google products or services, unless the policies expressly state that they are amending specific terms of service or agreements.