get_pr_diff

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

Describes read-only, non-destructive operation. No annotations, but 'fetch' and 'raw' adequately convey safety and no side effects.

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?

One sentence, 13 words, no filler. Efficient and front-loaded.

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?

Covers purpose and output adequately for a simple fetch tool. Lacks mention of return format, but 'raw diff' suffices.

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?

Only pull_number described in schema (33% coverage). Description doesn't detail owner/repo, but names are self-explanatory. Minimal added value.

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?

Spells out verb 'Fetch', resource 'raw file-by-file diff', and distinguishes from siblings like 'review_pr' by specifying 'with no AI review applied.'

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?

Implies use for raw diff without AI review vs. review_pr which applies AI review. Clear context but no explicit when-not or alternatives.

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