ado_pipelines_trigger

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

Annotations already declare readOnlyHint=false, but the description adds substantial behavioral context: it explicitly labels the operation as WRITE, states it 'immediately queue[s] a run,' and warns that it 'consume[s] build minutes.' This goes beyond the annotation by disclosing the side effect and resource cost, plus the vso.build_execute PAT scope requirement. The description does not detail idempotency or run lifecycle, but for a trigger tool with readOnlyHint=false, this is sufficient.

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?

The description is two sentences, highly efficient, and front-loaded with the primary action. It packs essential information—write nature, immediate effect, cost, optional overrides, and auth scope—without any fluff or redundancy. Every word earns its place.

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?

Given the tool's complexity (5 parameters, a nested variables object, and an array of stagesToSkip), the description covers the key behavioral aspects: the write action, the immediate queueing, the cost, and the required scope. It does not explain how to obtain pipelineId or project names, but those are operational details likely visible in sibling tools. No output schema exists, so return values are not expected. The description is adequate for an agent to correctly invoke the tool.

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?

The input schema covers all five parameters with clear descriptions (project, pipelineId, branch, variables, stagesToSkip), achieving 100% coverage. The description only paraphrases the optional parameters ('override the branch, set pipeline variables, or skip stages') without adding new semantic detail, such as examples, defaults, or cross-parameter constraints. With full schema coverage, the baseline is 3, and the description does not elevate it.

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?

The description clearly states the specific verb and resource: 'Queue a new pipeline run' with the target being Azure DevOps. It explicitly identifies itself as a WRITE operation, which distinguishes it from sibling read/list tools like ado_pipelines_list_runs and ado_pipelines_get_run. The mention of optional branch/variable/stage overrides further specifies its scope.

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 establishes the primary use case (triggering a new pipeline run) and implicitly differentiates it from read-only siblings by emphasizing the write nature and cost (consuming build minutes). It also notes the required PAT scope, which is a prerequisite. However, it does not explicitly name alternative tools or state when NOT to use this tool, leaving some inference to the agent.

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