Compare two refs

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

Annotations already declare readOnlyHint=true, so safety is covered; the description adds non-obvious behaviour instead: it never returns a patch because branch diffs are unbounded, the file list is capped by `max_files` and a capped answer is labelled as such, the `merge_base` used is printed, and both resolved commits plus `synced_at` appear in the result. These are real operational traits an agent cannot get from the annotations.

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?

Front-loaded with the core operation and output format before the caveats, and essentially every sentence carries information. It is a dense single paragraph with several interleaved concerns (capping, rename narrowing, no-history case), which costs some scannability but no obvious filler.

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?

There is no output schema, so the description must carry the return contract — and it does: per-file status letters (`A`/`M`/`D`/`R091 old -> new`), ± counts, `binary`, printed `merge_base`, resolved commits and `synced_at`. Combined with the cap semantics and sibling routing, an agent has everything needed to call and interpret this tool.

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 earns an extra point by explaining consequences the schema only hints at — that narrowing with `path` can turn a rename into a delete plus an add, and that a `merge_base="none"` result signals unrelated histories. The `merge_base` toggle is largely restated from the schema, keeping this short of a 5.

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 precise verb and resource — summarise what changed on `to` since it split from `from` — and pins down the exact git operation (`git diff <merge-base> <to>`) and output shape (one row per file with status letter and ± counts). It also differentiates itself from the sibling `diff_file`, so an agent can pick between them without opening either schema.

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?

Explicitly routes the agent: use `diff_file` for a single file's patch, and pass a printed `merge_base` as `from` to get the branch view of it. It also states the conditions that change behaviour (`merge_base: false` for the raw two-dot diff, no shared history ⇒ two-dot with `merge_base="none"`), leaving nothing to inference.

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