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

Beyond the annotations, the description discloses that login is required, that the goal is persistent, that there is no persistent request dedup key, and that the agent should query the current state rather than auto-retry after a timeout. This is especially valuable since idempotentHint=false alone does not convey the concrete retry behavior needed to avoid duplicate goals.

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 description is compact and every sentence carries operational value: creation semantics, timeout handling, and a pre-creation check plus downstream id usage. It is front-loaded with the core purpose and contains no filler or redundant restatements of the schema.

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 create tool with no output schema, the description covers essential operational needs: auth requirement, duplicate avoidance via get_my_work, non-idempotency handling, and the returned id's use in subsequent tools. However, the lack of parameter semantics for title and intent means an agent still has to guess at their exact meaning, preventing a perfect score.

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 33% — title and intent have no descriptions in the schema. The tool description adds no parameter-level meaning; it never explains what 'title' or 'intent' should contain or how they relate to the goal. Given the low coverage, this is a clear 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 opens with a specific verb and resource: '创建一个持久的独行录合作目标' (create a persistent collaboration goal) and clarifies that '用户成为发起人' (the user becomes the initiator). This clearly distinguishes the tool from siblings like create_collaboration_task by naming a distinct resource and describing its key semantic.

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?

The description gives explicit instructions on when to use this tool: '先 get_my_work 核对已有目标，再创建' (first check existing goals via get_my_work, then create), and how to handle uncertain outcomes: '结果不明或超时后先查询现值，不要自动重发'. It does not explicitly contrast with create_collaboration_task, but the preconditions and follow-up id usage imply a well-defined workflow.

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