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

Annotations already declare destructiveHint=true, idempotentHint=false, readOnlyHint=false and openWorldHint=true, so safety is covered structurally. The description adds the eligibility constraint (queued/in-progress only) and a consequence warning about half-finished deploys, which is real added value. However, the warning is oblique — it does not say plainly that cancelling mid-deploy leaves the site in an inconsistent state, nor does it mention permissions or whether the cancel can be undone.

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 short sentences, front-loaded with the action and its eligibility constraint, with no filler. The second sentence is a worthwhile warning but is phrased vaguely enough ('can leave a site half updated') that it costs a reread.

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 only two required parameters, full schema coverage, and annotations that carry the destructive/non-idempotent profile, the description covers what the agent needs to select and invoke the tool. It stops short of stating the post-cancellation state of the run or that the action is irreversible, which would have made it complete.

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%, so both parameters (repo with its owner/name example, run_id sourced from gh_actions) are already fully documented in the schema. The description only repeats the provenance of run_id that the schema already states. Baseline 3 applies since the schema carries the load.

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?

States a specific verb and resource ('Cancel a GitHub Actions run') with a state qualifier ('queued or in progress') and points at the source of the identifier ('run_id from gh_actions'). This is enough to distinguish it from list/inspect siblings like gh_actions, but it never contrasts itself with gh_actions_rerun or gh_actions_rerun_failed, which act on the same resource and are the most likely confusion points.

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 gives a clear precondition for use — the run must be queued or in progress — so the agent knows this is not for completed runs. The closing sentence signals that cancellation carries a cost ('a deploy stopped halfway can leave a site half updated'), which is usage context rather than an alternative-tool routing rule. No explicit when-not or alternative tool is named.

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