Compare reports from before and after a change

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

Annotations already cover safety (readOnlyHint true, openWorldHint false), yet the description still adds real behavioral content: the exact verdict set, the rule that a problem only counts as gone when a complete run verified it, and that early-stopped runs are never treated as fixes. It does not discuss failure modes for invalid report paths or how verdicts are weighted, keeping it below 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?

Three dense sentences, all front-loaded: purpose and return shape first, then the correctness rule, then the input-volume hint. No sentence is redundant and nothing is buried.

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 carries the return value and does so by naming the verdicts and the Markdown block, which is enough for an agent to know what comes back. The remaining gap is minor: it never says what happens when the sides are from different checks or how a bad path surfaces.

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. The description does add meaning to the array parameters — it explains why multiple reports per side are allowed (repeated runs) and gives the label parameters concrete purpose ("such as main and a branch"), but it contributes no format details beyond 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?

The description gives a precise verb and resource ("compares reports of the same check from before and after a change") and enumerates the full verdict vocabulary plus the returned artifacts (per-problem outcome, Markdown PR block). It does not name the closest sibling (verify_change) or state how it differs, so it stops short of full sibling differentiation.

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?

"Give several reports per side for repeated runs" is an explicit usage instruction, and the "complete run" rule tells the agent when a comparison result is trustworthy. There is no guidance on when to prefer verify_change or what to do when inputs come from a single run, so exclusions are absent.

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