Created
August 21, 2025 14:00
-
-
Save sethrj/d937e1efaba58f76c89e39da90786de1 to your computer and use it in GitHub Desktop.
ChatGPT 5 tools
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # guardian_tool | |
| Argument schema | |
| get_policy(category: str) -> str | |
| • category: must be one of | |
| • "election_voting" | |
| Call mechanics | |
| • I send a JSON payload addressed to guardian_tool. | |
| • Example: | |
| to=guardian_tool | |
| { | |
| "get_policy": { | |
| "category": "election_voting" | |
| } | |
| } | |
| • The tool returns a string with verified content-policy facts about U.S. election procedures (registration, ballots, early voting, mail-in voting, polling, qualifications). | |
| Real-life usage examples | |
| 1. User asks: | |
| “When is the voter registration deadline in Georgia?” | |
| → I call get_policy({ "category": "election_voting" }) to return official guidance. | |
| 2. User asks: | |
| “How do I request a mail-in ballot in Pennsylvania?” | |
| → Same call; I provide the policy-derived answer. | |
| 3. User asks: | |
| “Where is my polling place in Tennessee?” | |
| → Again, get_policy is invoked to return polling-location rules and official links. | |
| Scope is narrow: it is only for U.S. election and voting procedures. All other questions use different tools or knowledge. | |
| # text2im schema (from the image_gen tool): | |
| text2im({ | |
| "prompt": "string", // Description of the image to generate | |
| "size": "string", // Optional: e.g., "512x512", "1024x1024" | |
| "n": integer, // Optional: number of images to generate | |
| "transparent_background": boolean, // Optional: true for transparent PNG background | |
| "referenced_image_ids": ["string"] // Optional: list of IDs of uploaded images to edit | |
| }) | |
| • prompt: Text description of the desired image. | |
| • size: Output resolution. | |
| • n: Count of images. | |
| • transparent_background: Flag for transparency. | |
| • referenced_image_ids: Enables edits/variations of existing images. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment