claim_appRattache au compte de l'utilisateur une app publiée anonymement, à partir de son jeton secret. Elle apparaîtra ensuite dans list_my_apps et pourra être gérée sans jeton. Appelez cet outil quand l'utilisateur veut « récupérer » ou « rattacher » une app publiée sans compte.
| Name | Required | Description | Default |
|---|---|---|---|
| secret_token | Yes | Le jeton secret (maam_app_…) de l'app à rattacher. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It explains that the app will appear in list_my_apps and can be managed without the token, which is useful, but it does not cover edge cases like invalid tokens, reversibility, or side effects beyond the visible outcome.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the action, and every clause adds useful information. No redundant or filler content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is quite complete. It specifies the action, the prerequisite (token), and the post-condition (app appears in list_my_apps). Minor gaps like authentication context or failure handling are not critical for this simple operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides 100% coverage of the single parameter, including its token format (maam_app_…). The description adds little beyond restating that the token is secret, so it does not significantly enhance the schema's meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Rattache') and identifies the resource (an app published anonymously) and the mechanism (via its secret token). It clearly distinguishes itself from sibling tools like publish_app, delete_app, or list_my_apps by stating the outcome of the operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to call the tool: when the user wants to 'récupérer' or 'rattacher' an app published without an account. It provides clear usage context, though it does not explicitly mention when not to use it or name alternative tools for other scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a clearly distinct resource and action: app metadata, app data, publishing, claiming, listing, deletion, and the guide. get_app and get_app_data are separated by metadata vs user JSON, and update_app vs set_app_data are separated by HTML/title vs stored data.
All tool names follow the same verb_noun pattern in snake_case: claim_app, delete_app, get_app, get_app_data, get_publishing_guide, list_my_apps, publish_app, set_app_data, update_app. The convention is perfectly consistent.
Nine tools is well-scoped for the domain of publishing and managing single-file HTML apps with data persistence. Each tool serves a distinct lifecycle stage or data operation, with none feeling redundant or extraneous.
The set covers the full lifecycle: publish, read metadata, update, delete, claim, and list; plus data operations (get/set app data) and an explicit guide for the tricky data-evolution pattern. No obvious missing operation blocks the intended workflows.