read_pr_diff

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

With no annotations provided, the description carries the burden of expressing behavioral traits. It explicitly frames the operation as 'Read' and 'read a PR diff,' which strongly indicates a non-mutating operation. It also explains the target's selection behavior (most recent by default or specific diff via commit/file path). It doesn't cover edge cases like missing diff files or parameter conflicts, but the core behavioral intent is clear and supported.

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 front-loads the primary behavior ('Read the most recently generated PR diff file') and then appends the optional two selection modes. There is no redundant wording or restatement of the tool name, and every word contributes to the tool's meaning.

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 simple two-parameter, read-only tool with no required parameters, no output schema, and no annotations. The description covers the main invocation paths that an agent needs: read latest by omitting parameters, or read a specific diff by supplying a commit hash or file path. It omits details like error handling when no diff exists or combined parameter behavior, but those are minor for this straightforward tool.

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 must add meaning to the parameters on its own. It does: 'commit hash/file path' directly maps to the commitHash and filePath properties, and clarifies that these modes override the default most-recent behavior. It doesn't explain the exact path semantics or how the two parameters interact if both are provided, but it gives enough information to correctly choose an optional parameter.

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 uses a specific verb ('Read') and a clear resource ('PR diff file'), and immediately distinguishes between the default behavior (most recently generated) and the alternate modes (specific commit hash or file path). This clearly separates it from siblings like generate_pr_diff, get_pr_review_template, and save_pr_review.

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 states the main use cases: read the latest generated diff or read a specific diff by commit hash or filePath. It implies this tool should be used after a diff has been generated, which gives useful context. It does not explicitly name alternatives, but the sibling tools are self-evidently different, so only minor additional guidance would be needed.

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