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

Annotations only declare the generic write/open-world profile, yet the description adds substantial context: requires login, consumes model budget, writes proposals, per-org rate limit of 10/hour, ~50s latency, do-not-poll guidance, and the fact that generation does not notify while invitations are confirmed separately. This is exactly the behavioral load the annotations cannot carry.

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?

Dense but front-loaded: the bracketed 【需登录·花模型预算并写提案】 puts the critical prerequisites first, and each subsequent clause covers a distinct concern (modes, permissions, param semantics, rate limit, notification behavior). It is nearly waste-free, though the single sprawling paragraph is harder to scan than it could be.

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 high-complexity write tool with no output schema and low schema coverage, the description covers prerequisites, modes, key parameters, rate limits, latency, and post-generation state, and even explains the `note` output's intended meaning. Two input parameters (feed, refresh) go undocumented, which is the only real 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?

With schema description coverage at 14%, the description does the heavy lifting: it explains kind (PAIR/GROUP), hint semantics, that includePublic applies only to PAIR, and that maxParticipants is a recommended invite cap of 4–100 (default 50), not a signup/attendance count. It leaves feed and refresh unexplained, which keeps it out of the top band.

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 (生成对接/拉会提案) and splits it into two concrete modes, PAIR (two-person match) and GROUP (pull a meeting), which lets an agent tell it apart from siblings like list_organization_proposals or introduce_organization_proposal. It stops short of naming those siblings explicitly, so an agent must infer the distinction from mode semantics rather than routing language.

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 real selection logic: no-hint searches the matching network, a hint searches by topic (including cloud users), and it explicitly warns 勿轮询生成. It does not, however, say when to prefer this over adjacent tools such as search_organization_match_people or introduce_organization_proposal.

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