记录执行回执

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

Annotations are all false and carry no safety signal, so the description bears the burden. It adds 'only records facts' but does not disclose idempotency, duplicate handling, permissions, or side effects of attaching a receipt; it does not contradict annotations.

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?

Two short sentences with no fluff; the key action and semantic caveat are front-loaded. It is efficient, though the 7-parameter tool would benefit from more structured detail.

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?

With no schema descriptions, no output schema, and non-informative annotations, the description is too thin for an agent to invoke reliably: required fields, payload shape, status values, and relationship to task_id/external_id are all left implicit.

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 0% and none of the 7 parameters (project_id, action_type, status, occurred_at, payload, external_id, task_id) are explained in the description. The phrase '外部平台已经返回的执行凭证' hints at context but maps to no parameter, so the description adds almost no semantic value beyond field names.

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?

Description names the action ('保存'), the resource ('外部平台已经返回的执行凭证'), and adds a semantic boundary ('只记录事实...不把回执等同于最终业务结果'). It stops short of explicit differentiation from the sibling evidence_add, so it is not a 5.

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?

Implies when to use: when an external platform has already returned an execution receipt, and clarifies it is not a statement of final business outcome. But it gives no explicit alternative routing or when-not-to-use conditions vis-à-vis evidence_add or decision_create.

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