Doco Refresh Concept Candidates

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

Annotations already provide idempotentHint=true and destructiveHint=false; the description adds useful behavioral detail by specifying that writes automatically carry an idempotency key and that only pending-review candidates are generated, not direct changes to the explicit concept layer. This refines and contextualizes the annotation hints without contradicting them.

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 only two short sentences, with the primary action and the key safety guarantee front-loaded. Every phrase carries meaning, and there is no filler or unnecessary elaboration.

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 single-parameter tool with full schema coverage, idempotency annotation, and an existing output schema, the description provides sufficient information for correct selection and invocation. The absence of an explicit sibling alternative pointer is a usage-guideline nuance, not a completeness 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?

The single parameter document_id is fully documented in the input schema ('要重新抽取候选的文档 ID'), and the description adds no additional parameter-level semantics. With schema description coverage at 100%, the baseline score of 3 is appropriate.

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 names a specific action ('触发概念候选抽取/刷新') and resource ('概念候选'), and distinguishes this from the explicit concept layer by stating it only generates pending-review candidates. This makes it easy for an agent to tell it apart from siblings such as doco_concepts and doco_edit_concepts even without naming them.

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 clearly communicates when to use the tool: to trigger candidate extraction/refresh while avoiding direct pollution of the explicit concept layer. It does not explicitly name an alternative or give a when-not-to-use statement, but the safety boundary and 'pending-review' wording provide enough context for correct selection.

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