reject_decision

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

With no annotations, the description carries the burden and does disclose real behavioral traits: the backend does not restrict state transitions (a rejected decision can later be adopted again) and the MCP layer performs no pre-validation. What it omits is the failure mode — what happens if decision_id does not exist — so it's strong but not exhaustive.

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?

Front-loaded with the action and resulting state, then example phrasing, then caveats — a sensible order. The example-question list is a little verbose, but each line maps to a distinct user phrasing and earns its place for intent matching.

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 one-parameter mutation with no annotations, the description covers outcome state, the re-adoption/state-flow caveat, and the no-pre-validation warning; the output schema covers return values. Missing only error behavior and ID provenance, which are minor at this complexity.

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%, so the description must compensate; it does say decision_id is required and that the caller should confirm the ID before operating. It does not explain where the ID comes from (e.g. list_decisions) or what type/format it takes, so a meaningful gap remains.

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?

States a specific verb and resource ('拒绝一条决策建议') and the resulting state ('状态变为 rejected'), so the effect is unambiguous. It does not name adopt_decision or review_decision as the contrasting siblings, so it stops short of full differentiation.

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 example user utterances ('这条建议不采纳', '拒绝那个提价建议') give concrete intent-matching context for when this tool applies, and the ID-verification note sets a precondition. There is no explicit when-not guidance, e.g. 'to approve instead, use adopt_decision', so routing between the decision siblings still needs inference.

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