review_decision

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

With no annotations, the description carries the full burden and does disclose a non-obvious consequence: passing only free text without review_result means the review will not be counted in statistics. That is real behavioral value beyond the name. It still omits whether a repeated review overwrites a prior one, or what errors occur for an invalid decision_id.

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 purpose is front-loaded, followed by example queries and a compact parameter block. The closing 说明 partially restates the parameter section (text vs. enum), which is mild but justified redundancy given the statistical side effect it warns about.

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?

An output schema exists so return values need not be explained, and the parameters are well covered. However, for a mutation tool with zero annotations, it never states prerequisites—must the decision already be adopted/executed, and is re-review allowed—leaving an agent unable to predict failure modes.

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 description compensates fully: it explains decision_id, marks review_outcome as required free text with a concrete example ('降价后 7 天销量 +12%'), and enumerates the three review_result values effective/ineffective/inconclusive that appear nowhere in the schema. It also clarifies the division of labor between the two review fields.

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 concrete verb and resource: review a decision and record its actual post-execution effects, which clearly differs from create/adopt/reject in the sibling list. It does not explicitly name those siblings as alternatives, so differentiation is inferred rather than stated.

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?

Three example user phrasings plus the temporal cue '执行后' make clear when this tool applies (after a decision has been carried out and results are known). It stops short of exclusions—it never says what to do if the decision was never adopted or is still pending.

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