weekly_report

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

With no annotations, the description carries the full burden and discharges it: it specifies the returned JSON fields, the meaning and immutability of slots.id and loc, that it never creates drafts or exposes HTML, that the Server auto-advances Subject dates and chooses Reply All vs new draft, and the exact token-reuse/expiry rules. This is unusually rich disclosure for a mutation-style workflow.

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 text is long but dense, front-loaded with the identity claim and the critical semantics of `request` before moving to return shape and workflow. Given the complexity of the slot-routing and token lifecycle, most sentences earn their place, though a few procedural details could be trimmed.

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?

An output schema exists, yet the description still helpfully covers the return payload, token lifecycle, subject auto-advance, and the two-step continue_action handoff, so the workflow is complete. The main shortfall is the undocumented non-required parameters, which leaves how the tool sources prior weekly reports implicit.

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?

Schema description coverage is 0% across 6 parameters, so the description must compensate. It thoroughly explains only `request`; folder, folders, lookback_days, subject_contains, and reference_materials (a nested object array) are never explained, leaving an agent to guess how prior reports are located or what reference_materials should contain.

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 declares itself the sole Agent entry point for weekly-report (周报) requests, a specific verb+resource, and explicitly distinguishes itself from siblings by stating it does not search other people's mail (search_mail/read_mail do). An agent can tell it apart from the mail and draft tools without opening schemas.

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?

It gives explicit when-to-use sequencing: do search_mail/read_mail + LLM summarization first, then pass the summarized result as request, and specifically warns not to pass meta-instructions like '去搜索并总结 A、B' verbatim. It also names the follow-up tool (continue_action) and the conditions for re-invoking weekly_report.

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