repair_verify

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

The description declares 'Read-only', but the annotations set readOnlyHint=false, and the tool itself persists a new scan run (it returns a verify scan run id) — so the read-only claim directly contradicts the structured safety metadata. Beyond that contradiction, it does disclose the comparison categories (fixed/persistent/new) and the return payload, but the false safety claim is the kind of error that misroutes an agent.

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?

Two tight sentences, front-loaded with the action before the comparison detail and return values, so an agent gets the gist from the opening clause. The standalone 'Read-only.' fragment is short but misleading, which keeps this from being flawless.

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?

With no output schema, the description usefully summarizes the return ('verify scan run id and comparison counts') and the issue categorization (fixed/persistent/new), which is what an agent needs to interpret results. The main gap is the unresolved read-only/readOnlyHint discrepancy and the absence of any prerequisite or failure behavior.

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?

One parameter (repair_run_id) with 0% schema description coverage, so the description must carry the burden. It only obliquely references it via 'a repair run' and never states the accepted identifier form, where to obtain it, or whether it must be a completed/apply run. The parameter name is self-explanatory enough to reach a baseline 3, but no real semantics are added.

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 ('Verify a repair run') plus the mechanism ('re-scan the repaired copy') and the output semantics ('remaining issues vs the original scan (fixed/persistent/new)'). This clearly separates it from the sibling repair_propose_batch / repair_apply_batch / repair_rollback_batch tools without needing to open any schema.

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?

Usage is implied by the name and the phrase 'Verify a repair run', which points at the post-apply step, but there is no explicit when-to-use, no prerequisite (e.g. a prior apply run), and no named alternative such as list_issues or scan_file for a plain scan. Adequate but leaves the agent to infer the workflow position.

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