gh_create_pr

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

Annotations already mark this as destructive/write, but the description adds valuable context: the tool requires an environment variable to be enabled and by default prompts a human for approval before execution. This goes beyond the boolean hints and helps the agent anticipate guardrails.

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 two sentences with the purpose front-loaded. The second sentence adds critical enable/approval context without unnecessary padding, making it efficient 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?

With 10 parameters and no schema descriptions, the description is insufficient. It omits parameter semantics, especially the head/base branch distinction, and does not explain optional fields like draft, labels, or assignees. Even though an output schema exists, the input side is underexplained.

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 schema has 0% description coverage, and the description provides no parameter explanations. GitHub-specific terms like 'head' and 'base' are left undefined, so the agent must guess their meaning from parameter names alone.

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 'Create a new pull request in a repository' with a specific verb and resource. This distinguishes it from sibling tools like gh_create_issue or gh_get_pr.

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 does not compare this tool to alternatives, but it does imply usage via the purpose statement. It also provides operational context by noting the tool is disabled unless MCP_GH_ALLOW_WRITE_COMMANDS=true, which is useful for deciding when it can be used.

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