cmmn-claim_complete_with_evidence

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

With no annotations, the description fully covers the behavioral outcomes (satisfied completes task, not_satisfied returns judge_rejected halt with per-criterion verdicts, uncertain returns user_review_required). It also notes the fallback semantics. Missing detail on any side effects beyond task status changes, but otherwise comprehensive.

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 four sentences, each adding distinct information: purpose, outcomes, fallback. No wasted words, front-loaded with key purpose and behavior.

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?

Given no annotations, no output schema, and 4 parameters, the description covers all necessary context: evaluation logic, three outcomes, fallback, and parameter semantics. It even references future functionality and sibling tools, making it self-contained.

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 100%, so the description adds value by explaining semantics: evidence keys must match required_evidence and per-verifier args.key (referencing another tool), output_summary is for audit and future LLM use, result is optional pass-through. This goes beyond the schema descriptions.

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 it is a Judge-layer task completion tool, specifying the resource (task with acceptance criteria) and the verb (complete with evidence). It distinguishes itself from the sibling cmmn-complete_task by describing the fallback behavior when no acceptance criteria exist.

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 explains when to use the tool (when evidence is available to evaluate acceptance criteria) and provides context for when not to use it (tasks with no acceptance criteria fall through to cmmn-complete_task). It also mentions future plans for LLM judging, giving an implicit alternative.

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