Github Get Workflow Runs

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

Annotations already cover the read-only, non-destructive, open-world profile, so the description's real contribution is the wait semantics: polling until every run completes, a server-side cap so a task finishes before its worker is reassigned, and the meaning of timed_out when a run was still incomplete. That explains the otherwise puzzling idempotentHint=false for a read tool. It still omits error behavior and how the cap value is chosen.

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 opening sentence is well front-loaded, and the wait/timed_out sentences each earn their place. However, 'See #537' is an opaque issue reference with no resolvable meaning for an agent, and the skill cross-reference adds tail clutter that dilutes an otherwise tight paragraph.

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?

An output schema exists, so return-value documentation is not required, yet the description still explains the semantically important timed_out field. Behavioral edge cases are covered for the wait path. Minor gaps remain: what happens if neither run_id nor head is supplied, and how errors or an empty run set are reported.

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 only 60%, and the description compensates: it establishes that head means 'branch, tag or SHA whose commit to read every run of' and is mutually exclusive with run_id ('in place of run_id'), and it explains wait_seconds as a polling window that the server caps. repo_owner and repo_name remain unexplained but are self-evident.

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 and resource ('Reads a workflow run') and enumerates both selection modes: by id, or every run on the commit a head names. It implicitly separates itself from github_dispatch_workflow by noting the run_id is the value that dispatch returns, but it never names a sibling tool outright to force differentiation.

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 clarifies when to use each selector ('by id, or every run on the commit that head names, in place of run_id'), which is genuine routing guidance. It does not say when to use this instead of adjacent tools like github_get_job_log or github_get_pr_status_checks, nor when a wait is worth requesting versus polling separately; the pointer to github_get_skill('pr-analysis') offloads conventions elsewhere.

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