set_collaboration_task_status【需要登录】被指派人：TODO→DOING（接受，会通知指派人）/DECLINED（婉拒）/DONE，DOING→DONE/DECLINED，DONE→DOING（撤销完成）；DECLINED、CANCELLED 是终态。只有指派人能把 TODO/DOING 撤回为 CANCELLED。不合法的转移返回 task_transition_invalid。DONE/DECLINED 的 note 会作为完成留言/婉拒理由并通知指派人。不能代替他人宣称工作已完成。结果不明或超时后先查询现值，不要自动重发；服务没有持久请求去重键。 用 list_collaboration_tasks(done=true) 或 get_collaboration_goal(includeClosed=true) 核对。
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | ||
| status | Yes | ||
| taskId | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does so: requires login, notifications sent to the assigner, invalid transitions return task_transition_invalid, notes surface as completion/decline messages, no persistent request dedup key, and a retry-after-timeout warning to query current value first. This is exactly the operational context an agent needs.
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 content is dense but front-loaded with the state machine, then the warnings, then the verification tools; nearly every sentence earns its place. It is tightly packed with fine-grained detail that could be more scannable, but no sentence is redundant.
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 complex mutation tool with no annotations and no output schema, the description covers authentication, allowed transitions, terminal states, error signaling, side-effect notifications, idempotency hazards, and post-uncertainty verification. Nothing an agent needs to invoke it correctly is missing.
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%, so the description must compensate, and it does for the two key parameters: the status enum's per-value transition meaning and the note's role as completion message/decline reason are both spelled out. taskId is not defined but is self-evident, leaving only a minor gap.
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 states a precise verb (report/set status) and resource (collaboration task) and lays out the full state machine, distinguishing it from the sibling set_organization_task_status by scoping to collaboration tasks and assignee/assigner roles. An agent can immediately tell what it does and how it differs from neighboring tools.
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 explicitly enumerates valid transitions, names terminal states (DECLINED, CANCELLED), states the role constraint that only the assigner can withdraw to CANCELLED, and points to fallback verification tools (list_collaboration_tasks, get_collaboration_goal). When-to-use and when-not-to-use are both concrete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.