Cancel pipeline

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description goes well beyond: it says exactly what is destroyed (running steps killed, pending ones skipped), which pipeline classes are rejected and why (half-finished deploy), and that the call returns the new status. The warning that logs and commit messages are authored by whoever pushed is a genuinely valuable behavioral safeguard not present in any structured field.

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 core action and effect in the first sentence, then refusals, then the alternative, then the invocation caution. Despite the density, every sentence carries decision-relevant information and nothing is repeated from the schema.

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 destructive three-parameter mutation with no output schema, the description covers effect, refusal cases, return value (new status), recovery path, and safety constraints. An agent has everything needed to decide whether to call it and what to expect.

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 repo, number and instance are already documented in the schema itself, which sets the baseline at 3. The description adds only the abstract notion of "the pipeline" being cancelled and does not clarify the string-vs-integer form of number or instance naming beyond what the schema states.

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 ("Cancels a pending or running pipeline") and immediately describes the mechanism: running steps killed, pending skipped. It distinguishes itself from siblings by naming restart_pipeline as the recovery path, so an agent can tell it apart from get_pipeline or trigger_pipeline without opening any 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 explicit when-not conditions: refused for deployment, tag and release pipelines, refused for pipelines not pending/running, and blocked pipelines awaiting approval are left to a human. It also names the alternative (restart_pipeline) and adds a direct instruction to call only when the user actually asked, with a stated reason for that caution.

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