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

With readOnlyHint=true already covering the safety profile, the description goes well beyond it: it discloses truncation ('up to 100 (truncated beyond)'), ordering ('newest first'), the candidate/approximate nature of results due to line shifting, and the semantics of linkType (message vs branch) and match=path. This is exactly the behavioral context an agent needs before trusting the output.

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?

Purpose is front-loaded in the opening clause, followed by scoping constraints, then caveats about result reliability. It is a single dense sentence with stacked parentheticals, which costs a little readability, but there is essentially no filler text.

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?

No output schema exists, so the description must characterize returns — it does so reasonably (who, which task, newest first, cap of 100). It stops short of describing the returned fields or pagination/limit interplay with the default of 30, which is a minor remaining gap for a tool of this complexity.

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, but the description adds real meaning the schema lacks — the linkType explanation (message = task key in message, branch = commit on task branch) and the match=path behavior where line ranges are ignored for that commit. The startLine-endLine relationship to range filtering is also clarified beyond the raw schema strings.

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 names a specific verb+resource (show who changed lines startLine-endLine of a file and in which task) and pins down the data source and ordering (commits synced to Kosmodrom, all branches, newest first). This distinguishes it from the nearest sibling, repo_blame, by tying results to task-linked commits rather than raw attribution.

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?

Usage context is implied through hard scoping rules — 'only task-linked commits are included' and 'results are candidates' — so an agent can infer this is for task-linked annotation, not exhaustive blame. However, no sibling alternative is named (e.g. repo_blame for non-task attribution), leaving selection partly to inference.

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