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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered and the closing 'Read-only' is largely redundant. The description nonetheless adds behavior the annotations cannot: the 70-point threshold that defines inclusion, newest-first ordering, the fields returned (opened time, size, author, repository), and pagination at 100 PRs per page.

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?

Three front-loaded sentences: filter and ordering first, then return shape and pagination, then use case. Almost every clause carries information, though 'Read-only' duplicates the annotations and the per-page count slightly repeats the page parameter description.

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 no output schema, the description correctly compensates by naming the returned fields and the page size, and it states the sort order. What remains unstated is minor for a read-only listing: what a risk score of 70 means in substance, and whether a maximum page exists.

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 100%, and both parameters (page, repositoryId) are documented in the schema itself, so the baseline is 3. The description reinforces the page-and-size pairing ('Returns up to 100 PRs per page; pass page to read further') but adds nothing about repositoryId filtering beyond what the schema states.

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 definition states a specific verb and resource plus a precise filter: open pull requests with deploy risk score >= 70 (High or Critical), ordered newest first. 'At-Risk' is thereby given an exact, verifiable meaning rather than being a vague label. It does not name get_open_prs or score_pr_for_deploy_risk, so the boundary with those siblings is only implied by the threshold rather than stated.

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 line 'Use this to prompt engineering leads to review risky work before it merges' gives a concrete motivating scenario, which is more than nothing. However, no rule selects this tool over get_open_prs (all open PRs) or score_pr_for_deploy_risk (scoring a single PR), and no exclusions or preconditions are given.

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