create_project_runner

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is covered. The description adds the endpoint and a serialization caveat ('JSON-encoded string fields must remain strings'), which is genuine extra context, but says nothing about the fact that a runner created this way may need a registration token before it can work.

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, action and endpoint front-loaded, no filler. It is tight, but its brevity comes partly from omitting things that matter rather than from efficient encoding.

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 mutating creation tool with no output schema and an unannotated nested body, the description should say what comes back (e.g. the runner object or a token) and what happens when registered=false. Neither is present, so an agent cannot predict the result of the call it is about to make.

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 reported as 0%, so the description is the only place an agent could learn parameter meaning — yet 'Supply API fields in body' adds nothing. It never names name, tags, active, webhook, is_default, or max_parallel_tasks, and the 'JSON-encoded string fields' hint is not tied to any identifiable field (webhook is the only string, and it isn't called out).

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 ('Add project runner') and pins it to an HTTP endpoint (POST /project/{project_id}/runners), so the agent knows this creates a project-scoped runner. It does not explicitly contrast with create_global_runner, which is the one adjacent call an agent could plausibly confuse it with.

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 when-to-use guidance, no prerequisites (project admin rights), and no alternatives named. The key decision an agent faces — create_project_runner vs create_global_runner, and set registered=false plus a registration-token flow — is nowhere acknowledged.

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