repository_diff

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

There are no annotations, so the text carries the disclosure burden. 'Return ... diff' communicates a read-only operation and names the input modes, but it does not clarify behavior such as whether untracked files are included, which combination of revisions is required, or what happens with null revisions.

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?

A single sentence with no filler; the verb, resource, and mode options are front-loaded and compact. Every part 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?

Despite an output schema, the tool has no annotations and zero schema description coverage for its four parameters. The one-line description leaves key combinations (staged with revisions, null vs explicit revisions) ambiguous, so it is not complete enough for reliable calling.

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%, and the description only partially compensates: it links 'staged' and 'revision-to-revision' to the corresponding parameters but never explains repository_path, the exact meaning of base_revision vs target_revision, or how staged interacts with the revision parameters. An agent is left to infer parameter semantics from parameter names.

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 ('Return'), a resource ('local Git diff'), and a clear scope with three modes: working-tree, staged, or revision-to-revision. This distinguishes it from sibling repository tools such as repository_status or repository_history.

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 implies when to use the tool: whenever a Git diff in one of the three states is needed. However, it gives no explicit guidance about when not to use it and does not name any sibling alternative.

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