anon_post_lostfound

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only mark it non-read-only, destructive and open-world; the description goes well beyond that by disclosing the auth gate, multipart encoding, the auto-generated WebP preview side effect (≤800px, ≤100KB), and exact 400 error conditions for bad foundAt and non-image uploads. This is the kind of side-effect and failure-mode disclosure an agent needs before calling a mutating tool.

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?

Purpose and permission are front-loaded, then validation rules, then the endpoint and the projectId clarification. Dense semicolon-packed clauses but each carries distinct operational information, so little is wasted.

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 nested-body, permission-gated upload endpoint with no output schema, the description covers auth, encoding, validation, side effects and identity resolution - nearly everything needed to call it correctly. It does not hint at the response (e.g. the new item id) needed for follow-up patch/delete calls, which is a minor remaining gap.

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?

Adds real meaning beyond the schema: name must be non-empty after trim, foundAt defaults to now and returns 400 「无效的时间」 when invalid, photo is a single image ≤20MB with an auto WebP preview. It is silent on note and foundLocation, so it is strong but not exhaustive over the nested body.

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?

States a specific verb+resource ("登记失物" / register a lost-and-found item) and pins the exact endpoint POST /api/projects/{id}/lostfound, which cleanly separates it from the get/patch/delete lostfound siblings. It does not explicitly name those alternatives, so it falls just short of full sibling differentiation.

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?

Gives concrete entry conditions: lostfound:manage permission (project:manage accepted, superadmin exempt) and the fact that the project is derived from the API key so no projectId is needed. It never states when to prefer this over e.g. patch_lostfound_item_id, so routing guidance is implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.