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

Annotations only supply destructiveHint=false, so the description carries the burden and does: login required, preview only (no save, no DM creation, no send), saved/sent flags scoped to this session only, and a clear authorization chain where viewing/editing a draft or a failed consultant run does not authorize persistence. This is substantially more than the annotation provides.

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?

There is little filler, but the content is a semicolon-packed wall of terse fragments mixing Chinese prose with English tokens (EXISTING/ADAPTED/DRAFTED/saved/sent), and it opens with '登录' rather than the tool's action. The authorization rules are important but not front-loaded or grouped, making the description harder to parse than its length warrants.

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 five-parameter, zero-required, no-output-schema tool sitting in a multi-step pipeline, the description covers the workflow position, authorization boundaries, and parameter roles well. The remaining gap is that it never says what the preview actually returns or how the EXISTING/ADAPTED/DRAFTED mode is chosen or surfaced, which matters given there is no output schema.

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 coverage is 0% and the schema declares no required fields, so the description's constraint 'peerId/conversationId 至少一项' is critical information found nowhere else. It also disambiguates ownership of entry points: needId/productId belong to the counterparty while focusNeedId is the caller's own. It stops short of explaining format, precedence when several IDs are supplied, or the needId-vs-productId tradeoff.

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 conveys a specific action: generate a cooperation plan for a target by reusing an EXISTING dedicated draft, an ADAPTED generic draft, or a DRAFTED new one, and it explicitly labels the result as preview-only. Combined with the name/title, an agent can tell this is a plan-drafting/preview step rather than a save or send. It falls short of 5 because the core verb is buried mid-sentence after '登录' and never stated in one plain clause.

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 names the alternatives and the exact conditions that select them: save_cooperation_plan only on explicit request ('仅明确要求才save_cooperation_plan'), edit_cooperation_plan_with_agent for follow-up on context/draft, and send_cooperation_request for sending with the saved updatedAt. It also adds negative guidance ('待确认非已保存', '勿循环起草'), which is rare and directly actionable.

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