layerfs_branch_diff_branches

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

Annotations already declare read-only, idempotent, non-destructive, so the safety profile is covered. The description adds genuinely new behavior: results are paged and line hunks can be omitted for cheaper payloads. It does not explain what a nextCursor looks like or what the page envelope contains, and the referenced 'nextCursor' is not a declared input name.

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?

Two tight sentences, front-loaded with the core operation before the modifiers. Every clause carries information; only the mismatch between 'nextCursor' and the schema's 'cursor' introduces noise.

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?

For a read-only paginated diff over two refs, the description plus annotations plus schema cover what an agent needs. Return shape sits with the (absent) output schema, and the read-only safety profile is fully annotated.

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% across six parameters, so the description carries the full burden. It only clarifies two of them (cursor, hunks); from, to, pagePos, and pageSize — including the surprising '^/' pattern on cursor and the 1000 cap on pageSize — receive no explanation at all.

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 — paging changed paths between two saved refs — which is more precise than a bare name restatement. It does not, however, distinguish itself explicitly from the nearby layerfs_branch_diff_commits or layerfs_fs_diff_files siblings, and 'saved refs' is slightly at odds with the 'branches' in the tool name.

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 explains mechanics (how to continue paging, how to turn off line hunks) but never says when to choose this over diff_commits or diff_files, or what preconditions a 'saved ref' must satisfy. An agent must infer the selection rule from sibling names alone.

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