PR checklist

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

With no annotations provided, the description must carry the full burden of behavioral disclosure. It states what the tool generates (summary, change list grouped by conventional type, checklist) but does not explicitly confirm whether the tool has side effects (e.g., only produces text vs. modifying PRs) or mention error conditions. This is a moderate gap given the absence of annotations.

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, well-structured sentence that efficiently front-loads the verb and resource, then defines inputs and output structure. Every clause provides useful information without redundancy, making it easy to scan and understand.

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 presence of an output schema covers return values, and the description adequately explains the tool's function and the composition of the generated Markdown. It doesn't mention preconditions or edge cases, but for a generative tool with no annotations, this is reasonably complete.

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?

The input schema already provides descriptions for all three parameters, and the description adds context by explaining how commits contribute to the summary/change list and how changedFiles affect the body. However, it essentially restates the parameter purposes without adding new semantic detail, so the baseline of 3 is appropriate.

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 action verb 'Build' and identifies the resource as a 'Markdown pull-request body' with clear inputs ('a list of commits' and optional 'changed files'). This clearly differentiates it from sibling tools like branch_name and commit_message, which focus on naming conventions rather than PR content generation.

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 the primary use case—generating a PR body from commits—and the optional changedFiles parameter hints at when to include additional context. It does not explicitly mention when not to use the tool or name alternatives, but the sibling tools serve obviously distinct purposes, making the selection context reasonably clear.

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