git.diff

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

Annotations already declare readOnlyHint=true, so the agent knows this is a safe read operation. The description adds useful behavioral context by stating it returns 'structured' changes and includes 'untracked files,' which clarifies the scope of the diff. However, it does not elaborate on the exact structure of the output, pagination, or any limitations, so the added value beyond annotations is moderate.

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 sentence that is front-loaded with the primary action and resource, and it efficiently adds the key detail about untracked files. There is zero wasted text, and every word contributes to the meaning. It is highly concise and well-structured.

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?

The tool is simple (one parameter, no output schema) and has read-only annotations, so the description covers the essential aspects: what it returns and a key edge case (untracked files). It does not describe the return format in detail, but given the lack of an output schema, some ambiguity remains. Still, for a straightforward diff tool, the description is largely sufficient for an agent to call it correctly.

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 0%, meaning the parameter has no description in the schema, so the description must compensate. The description mentions 'Task worktree changes,' which implies the task_id parameter selects the task, but it never explicitly names or describes the parameter's role. Since the schema already shows a single required string with minLength 1, the description adds minimal meaning but does not fully explain how task_id is used (e.g., whether it's a UUID or a human-readable name). This is adequate but not thorough.

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 clearly states a specific verb ('Return') and a precise resource ('structured Task worktree changes and unified diff'), adding the detail 'including untracked files' to further scope the output. It distinguishes itself from all sibling tools, none of which offer diff functionality, so an agent can immediately identify this as the diff tool.

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 usage by naming the purpose (returning changes/diff) but provides no explicit guidance on when to use it versus alternatives. Since no sibling tool performs diffs, the usage is self-evident, but there are no stated exclusions or context such as 'use before commit' or 'only when a task is active.' This meets the 'implied usage' bar but nothing more.

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