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

Annotations already cover the safety profile (readOnlyHint true, destructiveHint false), so the description's added value is the auth model: repository read access is required, the ci-audit token preset with runners/actions read scopes works, and repository tokens are not accepted on /mcp. That last point is a genuine operational gotcha an agent could not infer. It stops short of describing result shape or how much history is reachable, which keeps it at 4.

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?

The first sentence is a clean, front-loaded statement of purpose, but the remainder strings together an issue number, a REST endpoint mirror, and a lengthy token-preset recipe that reads like internal ticket commentary. The credential guidance is useful but could be one clause rather than several sentences of curl-level detail.

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 read-only list tool with seven parameters and no output schema, the description covers purpose, ordering, filtering, sibling relationships, and the exact credential needed, which is what an agent needs to invoke it correctly. What it does not cover — response fields, whether pagination is cursor or offset beyond the offset param — is minor given the schema's limit/offset parameters.

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 71%, so most parameters are already documented (limit default 30/max 100, offset paging, branch ref forms, status enum, event values). The description only adds that filtering is optional and that results are newest-first, which is ordering behavior rather than parameter syntax. Baseline 3 is appropriate since the schema does the heavy lifting.

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 first sentence gives a specific verb and resource (list a repository's workflow runs), states ordering (newest first), and names the filter dimensions. It also explicitly situates itself against merjax_get_workflow_run and merjax_cancel_workflow_run, so an agent can distinguish it from CI siblings like merjax_ci_queue_status without opening a 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?

It states precisely when to use this tool: to find run ids that will then be passed to get_workflow_run or cancel_workflow_run, and cites the concrete failure mode (#10493, stale queued runs undiscoverable) that motivates it. It also gives the alternative path (direct GET on the runs endpoint) and the credential required.

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