contribos_check

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

With no annotations the description carries the full burden, and it does disclose real behavior: the enumerated check domains, the conditional verify_test behavior ('whether the test fails without the fix'), and a constraint on the agent's own output. It never states whether the tool is read-only, whether it mutates the checkout, or how failures surface, which leaves notable gaps.

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?

Purpose is front-loaded, but the body is one long comma-chained sentence listing a dozen checks, which is hard to scan. Every clause is substantive, yet the structure is a run-on rather than a prioritized list.

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 7-parameter tool with no output schema and no annotations, the description covers the check surface well but omits return shape, side effects, and safety profile. It is adequate to call the tool, but an agent cannot predict what it gets back or whether the working tree is touched.

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 baseline is 3, but the description adds meaning by tying parameters to intent: issue maps to 'competing PRs', verify_test to the fail-without-fix check, ai_note/explanation to AI-disclosure and contributor-explanation evaluation. Only 'path' and 'base' are left purely to the schema.

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+resource: a pre-submit review of the local branch against the repo's rules and history. It enumerates the checks concretely (scope, tests, changelog, sign-off, AI policy, competing PRs), so an agent knows what the tool does. It does not, however, differentiate itself from the sibling contribos_review.

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 phrase 'Pre-submit review' implies the moment to use it, and 'Do not write the explanation for the user' is a useful boundary. But no alternative is named and neither contribos_review nor contribos_brief is contrasted, so the agent must infer which sibling applies.

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