complete_subtask

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

With no annotations, the description carries the burden and delivers real behavioral facts: artifacts land in /jobs/<job>/<key>/, success=false triggers a retry, and gate tasks require approve|reject. Missing auth/permission expectations and return behavior, so not a 5.

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?

Dense but front-loaded: the core action and the payload rule arrive first, edge cases (gate tasks, leftovers, success semantics) after. Sentence-per-line structure aids scanning, though a couple of clauses are compressed to the point of being terse.

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 16-param mutation tool with no annotations and no output schema, the description covers the crucial workflow behavior (artifact storage, retry semantics, verdict handling). The remaining gap is the metadata params, which are largely self-evident from their names.

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% across 16 params, so the description must compensate. It explains the meaningful ones (repo, branch, commit, diff, verdict, leftovers, preferences, success) but leaves subtask_id, result, agent, model, cost, tokens, tokens_in, and api_key undocumented.

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 ('Finish a claimed subtask'), and the workflow framing ('claimed') implicitly contrasts with claim_subtask and submit_task. It never names a sibling outright, so it stays at a 4 rather than a 5.

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?

Provides conditional routing guidance: pass repo/branch/commit/diff when code changed, verdict for gate tasks, leftovers/preferences for their specific payloads. The success=false rule is an explicit when-to-use boundary. No explicit alternative-tool routing, so not a 5.

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