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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false) by disclosing the enforcement surface — web button, API, MCP merge, merge queue, merge train, autopilot — plus the required 'repo' scope and write access. It also discloses the side effect that the body is posted as a comment and that only the caller or someone with write access can clear the block.

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?

Front-loaded with the action, then the consequence chain, then the permission requirement — a sensible ordering with no filler sentences. The single sentence is long with nested parentheticals (the six merge paths, the dismissal tool reference), costing some readability.

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 mutation tool with thin annotations and no output schema, the description covers effects, persistence, authentication scope, and side effects thoroughly. The only gap is what a successful call returns (review ID, state, or comment reference), which an agent may need for follow-up calls.

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 only 25%: 'body' is documented as Markdown, and the description adds that it is also posted as a comment, which is genuine added meaning. The remaining three required parameters (owner, repo, number) are not explained at all in either place, though they follow the conventional repository-PR convention used across this sibling family. Adequate but not compensating for the coverage gap.

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?

States a specific verb and resource ('Request changes on a PR') and immediately clarifies the underlying mechanic ('Records a changes requested review by the caller'), which distinguishes it from merjax_comment_pr and pairs it against merjax_approve_pr/merjax_dismiss_review. An agent can identify the correct tool without opening any schema.

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?

Explains the operative condition well: the review holds the PR on every merge path until approval or dismissal via merjax_dismiss_review, which tells the agent exactly when the effect persists and how it is undone. It stops short of explicitly stating the inverse case ('use merjax_approve_pr to approve, merjax_comment_pr for a non-blocking comment'), leaving that routing to inference from sibling names.

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