set_project_runner_active

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

Annotations already carry the safety profile (destructiveHint=true, openWorldHint=true, readOnlyHint=false), so the description's burden is reduced. It adds the concrete endpoint and a serialization warning that JSON-encoded string fields must stay strings, which is genuinely useful pre-call context. However, it never says what deactivating a runner does to in-flight tasks or whether the change is reversible, which is exactly the risk flagged by destructiveHint=true.

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?

Three short sentences, front-loaded with the action, then the endpoint, then the serialization caveat. No filler. Slightly weakened by the endpoint restating what the name already implies, but it is compact.

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 destructive, non-idempotent-flagged mutation with no output schema and 0% parameter documentation, yet the description never covers permissions, side effects on running jobs, or what the response confirms. For a state-changing runner operation on a shared CI resource, it leaves the agent materially under-informed.

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 0% across three parameters. The path template implicitly maps project_id and runner_id to URL segments, and the body is mentioned as 'supply API fields in body', but the actual body property (`active`, a boolean) is never named or explained, nor is the effect of true vs false. Compensation for the coverage gap is minimal.

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: 'Set project runner active state', which is clearly a state toggle on a project-scoped runner. The embedded path POST /project/{project_id}/runners/{runner_id}/active disambiguates it from update_project_runner and from the sibling set_global_runner_active. It stops short of explicitly naming that sibling, so it is clear but not differentiated in prose.

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?

No statement of when to use this versus update_project_runner (full runner config) or set_global_runner_active (global scope). No prerequisites such as required permissions or whether the runner must be idle. The agent must infer everything from the tool name and the path.

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