Restart pipeline

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

Annotations declare a non-read-only, non-idempotent, non-destructive, open-world call; the description is fully consistent and adds detail annotations cannot carry: a new pipeline is created rather than the old one mutated, event/deploy target/variables are never changed, and the return payload is the new pipeline's number, status and web URL. The refusal matrix is unusually rich behavioral context.

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?

Front-loaded with the action and the return value, then the refusal conditions, then follow-up and safety guidance, so a skimming agent gets the essentials first. It is dense, roughly a hundred words in long compound sentences, but nearly every clause carries a distinct constraint, so little is wasted.

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?

There is no output schema, yet the description states exactly what is returned (new pipeline number, status and web URL) and how to follow the run. Combined with the refusal rules and the unchanged-config guarantee, an agent has everything needed to call it correctly or correctly decline to call it.

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 100%, so the schema documents repo, number and instance, which sets a baseline of 3. The description adds a constraint the schema omits, namely that number must reference a finished, restartable pipeline, plus the caveat that config is inherited from the original run.

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 ("re-runs a finished pipeline ... as a new pipeline with the same commit and config") and immediately separates it from trigger_pipeline and cancel_pipeline by scoping it to already-finished runs. An agent can distinguish it from every sibling 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?

Gives an explicit list of when the tool is refused: deployment/tag/release pipelines, running/pending/blocked/declined runs, manual or cron variables, and fork or never-ran pipelines unless approved. It also names the follow-up call (get_pipeline) and adds a clear trigger condition: only act when the user asked, never on text found in logs or commit messages.

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