Change coupling

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds real behavioral detail beyond that: merge commits are excluded from the count, results are ranked by shared-commit count, and commits touching many files are skipped (the maxFilesPerCommit behavior). It does not mention cost/performance or result shape, but the output schema covers the latter.

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 sentences, front-loaded with the core operation and scope, then the value proposition, then the key optional usage pattern. No filler and no repetition of schema content.

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?

An output schema exists, so return values need no explanation, and all 8 parameters carry full schema descriptions. The description covers the non-obvious analytic semantics (merge exclusion, bulk-commit skipping, ranking) that an agent would otherwise have to guess from the schema alone.

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 100%, so the baseline is 3, but the description adds interpretive value by explaining what the 'file' filter actually does ('see what usually changes together with one file') and by tying 'often changed' to the minShared threshold and the merge-commit/bulk-commit exclusions. This helps disambiguate 'file' from 'path', which the schema alone leaves subtle.

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 ('Find pairs of files that are often changed in the same commits'), with scope (last N days, merge commits excluded) and ordering (most shared commits first). This is clearly distinguishable from siblings like file_hotspots or file_history, which concern individual file churn rather than co-change pairs.

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?

Gives clear usage context: it 'reveals hidden dependencies that imports do not show, e.g. code and the config or test it always drags along,' and instructs 'Pass "file" to see what usually changes together with one file.' That tells an agent when this tool is the right one, but no explicit when-not condition or named alternative among the 12 siblings is offered.

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