git_diff

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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, fully covering the safety profile — the description need not restate this. The description adds the semantic scope (differences between branches or commits) but doesn't disclose what the output format looks like (e.g., unified diff, patch text) or mention the default of 3 context lines shown by the parameter default. That gap is modest, so a 3 is fair.

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?

The description is a single efficient sentence with no filler or repetition. It isn't front-loaded with a redundant restatement of the tool name. It earns a 4 for being appropriately sized, though a second sentence clarifying the target parameter would push it higher.

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?

This is a read-only tool with a trivial annotation profile, so no output schema is needed, but the description still leaves gaps. It doesn't specify valid 'target' formats (branch name vs. commit hash vs. range like 'main..dev'), doesn't say what the output looks like, and doesn't mention the context_lines behavior. For a three-parameter tool with zero schema documentation of those parameters, that is an incomplete definition.

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%, so the description carries the full burden for parameter semantics — and it fails to do so. The description mentions 'differences between branches or commits', which loosely maps to 'target', but says nothing about what 'target' should contain (a branch name, a commit hash, or a range), what 'repo_path' is, or what the optional 'context_lines' controls (number of surrounding lines shown in the diff). With all three parameters undocumented in the schema, the description would need to explain at least 'target' to earn a 3; it only gestures at it.

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 'Shows differences between branches or commits' provides a clear verb ('shows'), a specific resource ('differences between branches or commits'), and is unambiguous about what the tool does. It doesn't explicitly differentiate from sibling tools, but the resource is specific enough to distinguish it from common alternatives like git_log or git_show.

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 gives no guidance on when to use this tool versus alternatives. It doesn't state whether to use it for uncommitted working-directory changes, staged changes, or particular diff formats, nor does it mention branches/commits as alternative scopes. An agent is left to infer the appropriate context.

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