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

Annotations (destructiveHint=true) already indicate a destructive operation. The description adds valuable context: it lists the enforced checks (GateTest, AI-review, branch protection) and the soft-block behavior for critical risk scores. No contradiction.

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?

Two dense but clear sentences. Front-loaded with the core action and then details. No unnecessary words or repetition. Perfectly concise.

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?

For a complex merge tool with multiple gates and a risk-score override, the description covers the main behaviors. It also specifies the return object structure. However, it omits error conditions (e.g., what happens if merge fails due to a failing check) and retry behavior. Given no output schema, the return info is helpful but could be more explicit about failure scenarios.

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 100%, so baseline is 3. The description adds extra context for confirm_high_risk (bypasses critical-band soft-block), but other parameters (owner, repo, number) are not explained beyond what the schema provides. Adequate but not exceptional.

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 the tool merges an open PR and enumerates specific checks (draft, head SHA, GateTest, AI-review, branch protection), distinguishing it from siblings like close_pr or open_draft_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?

It explains that the tool enforces the same checks as the HTTP merge flow and describes the M3 risk-score soft-block and override. While it doesn't explicitly say when not to use it (e.g., for PRs that are drafts), the context from sibling tools and the description make it clear. Could be improved by contrasting directly with close_pr or request_changes.

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