analyze_test_gaps

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

Without annotations, the description carries the burden. It discloses that the tool is 'guidance only' (non-destructive) and requires a root path, but omits details about output format, performance characteristics, or whether it modifies files.

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 information-dense sentences with no waste. Main purpose is front-loaded ('Estimate missing tests...'). Parenthetical and trailing fragments efficiently pack constraints (requires root, guidance only) without verbosity.

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 100% schema coverage but no output schema or annotations, the description adequately covers inputs but only hints at output via 'guidance only'. For a file analysis tool, it should describe what the guidance/estimates look like or what format results take.

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% (baseline 3). The description adds valuable context: 'requires root' reinforces the required parameter, 'relative-path globs' clarifies path handling, and 'defaults include TS/JS/PY' documents implicit behavior not visible in 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?

Clearly states the tool estimates missing tests using source/test patterns. 'Guidance only' clarifies the output nature. However, it doesn't explicitly distinguish from sibling analysis tools like analyze_file or analyze_impact.

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?

Provides constraints like 'requires root' and 'Guidance only', and mentions supported patterns (relative-path globs) and default languages (TS/JS/PY). Lacks explicit guidance on when to use versus siblings like code_quality_analyzer.

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