verify_changes

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world; the description goes further by disclosing fingerprint comparison, the freshness of the audit, the conservative coverage rule (absence under incomplete coverage is unresolved, never resolved), and that it never enables validation commands or live DB access.

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?

Four front-loaded sentences, each carrying distinct load: purpose, mechanism and outputs, the interpretive rule, and the safety posture. No filler or redundant restatement of annotations.

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 correctly supplies the result vocabulary (resolved, unchanged, unresolved) and the coverage caveat, so an agent knows what comes back and how to read it. Nothing needed to invoke this tool correctly is missing.

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 3 applies, but the description adds real meaning: baseline is a prior codebase-doctor schema-1 JSON report on the machine, and the coverage caveat implicitly frames how results should be interpreted. This is slightly more than the schema conveys, though it does not detail base/changed/path interactions.

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 (verify) and resource (findings from a prior schema-1 JSON report being repaired), plus the mechanism (fresh read-only audit, fingerprint comparison). This is clearly distinguishable from audit_codebase's fresh audit because it is explicitly baseline-relative.

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 requirement of a prior baseline report plus the resolved/unchanged/unresolved framing makes the post-repair verification context clear. It stops short of explicitly naming audit_codebase or state a when-not condition, so it lands just below a full 5.

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