bb_get_diff

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

With no annotations provided, the description takes on the full transparency burden and does it well. It reveals that the diff is reconstructed by walking /commits/<sha>/diff along branch lineage from 'until' down to but not including 'from', and it documents the per-file output structure. It stops short of describing error behavior, authentication expectations, or performance implications of large diffs.

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 dense, purposeful sentences with no filler. The primary action and scope come first, then the default behavior, then the reconstruction mechanics and return format. Every clause earns its place.

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 tool with no annotations and no output schema, the description provides enough operational detail: required ref semantics, defaults, endpoint-walking behavior, and return contents. It could be more complete by explicitly contrasting with sibling diff endpoints or warning about non-linear history, but an agent can invoke it correctly from what is written.

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 50%: 'from' and 'until' have descriptions, while projectKey and repoSlug are self-evident from their names. The description adds meaningful semantics by saying 'from' is the exclusive base and 'until' is the inclusive head, and by stating the default for 'until'.

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: 'Get the full diff between two refs (commit SHA or branch name).' It also clarifies the exclusive/inclusive semantics of the refs and describes the return shape, making it reliably distinguishable from sibling diff tools like bb_get_diff_summary or bb_get_pull_request_diff.

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 clear usage context by defining the tool as a ref-to-ref diff operation, with the 'until' default and the walk direction explicitly explained. It does not name alternatives or state exclusions, but the ref-based scope is concrete enough for an agent to decide when to invoke it.

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