converge

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

The description adds significant behavioral context beyond annotations: it clarifies that evidence without reference/revision is not reviewable, explains rejection conditions, and states the monotonic nature of evidence requirements. This complements the annotations (idempotentHint=true, destructiveHint=false) by detailing exactly what the tool checks and rejects, without contradiction.

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 a single, front-loaded paragraph of three sentences. Every sentence adds essential information: the core function, rejection criteria, and parameter constraint. There is no redundancy or filler, achieving high density of useful guidance.

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?

The tool has 5 parameters, no output schema, and moderate complexity. The description covers behavior and constraints well but fails to specify what the tool returns on success (e.g., confirmation, next steps) or any side effects. Given the absence of an output schema, these gaps reduce completeness for an agent invoking the tool.

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?

With 60% schema coverage, the description compensates by explaining parameter behavior for 'required_evidence_kinds' (only additive, not removing) and 'feature_name' (triggers check_spec call). While 'docs_dir' and 'project_root' are not elaborated, the description adds meaningful constraints beyond the schema, earning above baseline.

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 clearly states the tool's purpose: to close a Delegated Plan by verifying its declared evidence and quality gates. It uses specific verbs ('收敛' meaning converge/close) and identifies the resource ('Delegated Plan'). This distinguishes it from sibling tools like plan_heartbeat (status check) and resume_plan (resume), making selection unambiguous.

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 provides strong usage context by detailing conditions for rejection (incomplete steps, missing evidence) and the constraint that parameters can only add evidence requirements, not weaken the Plan. While it does not explicitly name alternative tools, it implicitly advises using converge only when all gate criteria are met. The guidance is clear and actionable.

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