list_workflow_run_jobs

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful context beyond annotations by disclosing that 'job and runner names are untrusted repository content' and that 'steps and external URLs are excluded' from results. This is valuable security/behavioral context for an agent deciding whether to render or trust job output.

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 sentences, no filler. The first sentence states the core action and scope; the second adds a critical security note about untrusted content and excluded fields. Every word earns its place.

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?

This is a read operation with readOnlyHint and destructiveHint annotations, so the safety burden is reduced. No output schema exists, but the description doesn't need to detail the return structure for a list tool. The pagination and untrusted-content disclosures are sufficient. Slightly more detail on what 'bounded page' implies for callers (e.g., need to iterate) would push this to 5, but it's adequate.

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 14% (only 'repository' has a description: 'Repository in owner/name format'). The description doesn't explain individual parameters like attempt, page, perPage, or hostname. However, the description's phrase 'one bounded page' partially clarifies the page/perPage semantics. Baseline 3 is appropriate given the low schema coverage, but the description does contribute some pagination context.

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 uses a specific verb+resource combination: 'Read one bounded page of jobs for a GitHub Actions workflow run.' It clearly distinguishes itself from siblings like list_workflow_runs (which lists runs, not jobs) and get_workflow_job_log (which fetches logs, not job metadata). The phrase 'bounded page' adds purposeful scoping detail.

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 implies paginated reads (page/perPage parameters) and establishes the tool's scope relative to the run. However, it doesn't explicitly name alternative tools for listing runs or fetching logs, though the high-level behavior makes the use case clear. It would benefit from explicitly contrasting with get_workflow_job_log or list_workflow_runs.

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