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

Annotations only declare destructiveHint=false, so the description carries the behavioral load and does so well: login is required, model budget is consumed, ~10 calls/hour per organization, ~50 second latency, and generation does not notify anyone. It also discloses that candidate eligibility and permissions are decided server-side, which prevents the agent from assuming it controls the result set.

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?

Every clause carries information — cost, mode branching, permission boundary, parameter caveats, rate limit, and output expectation — with no filler. The semicolon-chained packing is dense and defers the core purpose behind the login/budget preconditions, so it is efficient but not optimally front-loaded.

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 7-parameter, budget-consuming generation tool with no output schema, the description covers the costly and risky behaviors an agent most needs: prerequisites, latency, throttling, non-notification, and the meaning of the returned note. The main residual gaps are the undefined feed and refresh flags and the absence of any statement about the shape of the returned proposals.

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 only 14% (organizationId alone), so the description must compensate, and it explains kind's two modes, hint's with/without semantics, includePublic being PAIR-only, and maxParticipants as a recommended invitation cap of 4–100 defaulting to 50 that is not a signup or attendance count. Two parameters, feed and refresh, receive no explanation anywhere, which keeps this below a 5.

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 names a specific verb and resource (generate proposals for an organization) and splits the operation into its two concrete modes, PAIR (two-person matching) and GROUP (convening a meeting), so an agent knows exactly what it will produce. The closing clause '生成不通知，邀请另行确认' also separates this generation step from the sibling invitation tools (introduce_organization_proposal, create_organization_proposal_activity).

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 branch guidance: with no hint the service searches the matching network, with a hint it searches by topic (including cloud users), and includePublic applies only to PAIR. It also warns '勿轮询生成' and states a per-organization hourly cap, but it does not say when to prefer an alternative like search_organization_match_people or list_organization_proposals instead.

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