anon_get_onsite_incidents

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

Annotations already cover safety (readOnly, idempotent, non-destructive). The description adds genuinely useful behavior beyond them: permission-scoped visibility, reverse-chronological ordering, and a hard 50-item cap — critical for interpreting results. It stops short of pagination details, so not a 5.

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?

Front-loads the action, then permission scope, ordering, limit, endpoint, and the no-projectId note. Every sentence carries information; no filler.

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 zero-param, annotation-backed read tool with no output schema, the description covers purpose, permissions, ordering, limit, and auth source. A note on response shape or pagination would make it fully complete, but nothing essential is missing to call it correctly.

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?

Zero parameters, so the baseline is 4. The description adds important context beyond the empty schema by explaining that the project is inferred from the current API key (no projectId needed) and by documenting the endpoint path.

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 (列出现场异常 = list onsite incidents) and clearly distinguishes the sibling family: there is anon_get_onsite (onsite overview) versus this incidents list, plus anon_post_onsite_incidents for creation. The purpose is unmistakable.

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?

Discloses permission-based visibility (work:manage/project:manage see all, ordinary members see only their own reports) and the ordering/limit, which tells the agent when the result may be incomplete relative to a manager's view. It doesn't explicitly name alternative tools, but the visibility caveat is real usage guidance.

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