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

Annotations already carry readOnlyHint, and the description restates 'Read-only' (mild redundancy) but goes well beyond: it discloses the withheld-log case and the required 'repo' scope for private repositories, the fact that a timed_out run still blocks merge, and the exact shape of the `failure` payload. That auth and blocking-behaviour context is real value the annotations cannot supply.

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?

It is front-loaded with the core purpose, which is good, but the remainder is a single ~180-word sentence stitched together with em-dashes and nested clauses that is hard to parse on a quick read. The detail is largely justified given there is no output schema, but the structure could have been broken into scannable clauses.

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?

There is no output schema, and the description compensates fully: it enumerates the returned fields (head_sha, total_count, check_runs, required, ci), the per-check state vocabulary, and the nested failure shape including the withheld variant. An agent can correctly interpret the response without any further documentation.

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% and all three parameters (owner, repo, number) are documented in the schema, so the description does not need to explain them. It adds nothing parameter-specific beyond the phrase 'at a PR's current head', which merely reinforces what `number` means. Baseline 3 applies.

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?

Opens with a specific verb and resource ('List every check at a PR's current head') and enumerates the covered sources (workflow runs, gates, commit statuses), so the agent knows exactly what is returned. It does not name the neighbouring tools (pr_status_summary, list_workflow_runs, get_workflow_run) that could be mistaken for it, so sibling differentiation is left implicit.

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?

There is no explicit when-to-use or when-not statement and no named alternative, despite siblings like pr_status_summary and list_ready_to_merge covering overlapping ground. The merge-readiness framing hints at intent, but the agent must infer it from the return-shape description rather than from any stated guidance.

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