explore_finding

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It doesn't mention whether this is read-only, what kind of evidence is returned (return format), whether refactoring guidance is included, or any side effects. The description is very sparse.

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?

The description is one short sentence plus a usage hint. It's efficient and free of waste, but it's also under-specified—brevity is not the same as thoroughness.

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 5 parameters at 0% schema coverage, no output schema, no annotations, and no mention of return format or behavioral constraints, the description is inadequate. The tool appears to be a complex evidence-retrieval operation (files, symbols, refactor) that needs more explanation of what evidence format to expect and how the multiple optional parameters interact.

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%, so the description must compensate. It only hints that `sessionId` is preferred (from review_project) but doesn't explain the relationship between `findingCode`, `findingId`, `path`, or `sessionId`, or how `limit` constrains results. With 5 undocumented parameters, this is insufficient.

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 states "Evidence for one finding (files, symbols, refactor)" which identifies the tool's purpose as retrieving evidence. However, it doesn't distinguish itself clearly from the sibling tool `explain_finding` or `review_project`, and the parenthetical types are vague.

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 description provides one useful usage hint: "Prefer sessionId from review_project," which tells the agent to prefer one parameter. However, it doesn't explain when to use this over `explain_finding`, when not to use it, or what the `findingId` vs `findingCode` distinction means for selection.

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