Trigger CI workflow

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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true), and the description adds value beyond them: the failure mode (GitHub rejects workflow_dispatch on workflows that lack the trigger), the cost/latency profile ('one API call'), and how the side effect becomes observable ('the new run appears in project_ci_status within ~10s'). It also enumerates the output fields (repo, provider, workflow, ref, inputs, triggered, dispatched_at), which matters since no output schema exists.

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 purpose, then labeled blocks (Use when / Avoid when / Speed / Output / Batch-safe) so an agent can scan to the relevant line. No filler sentences; each line carries a distinct operational fact.

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 6-parameter, zero-required, nested-object mutation tool with no output schema, the description supplies what's missing: which providers/pipeline types are covered, what the return payload looks like, the failure case, and the visibility delay. Nothing an agent needs to decide whether to call it or to interpret the result is absent.

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 83%, so the schema already documents ref, repo, provider, workflow, and reason in detail; the description only repeats the ref default ('Ref defaults to the current branch') which the schema already states. It adds light context for the undocumented nested `inputs` object ('dispatch a workflow with inputs/variables') but no value-type or naming guidance for it. Baseline 3 is appropriate given the schema does the heavy lifting.

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 (Trigger) plus the exact resources per provider: GitHub Actions workflow_dispatch, GitLab pipeline, Bitbucket custom pipeline. An agent can immediately tell this apart from the read-only siblings project_ci_status and project_ci_logs 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?

Explicitly gives both directions: 'Use when: re-running a pipeline for a branch without a new commit, or dispatching a workflow with inputs/variables' and 'Avoid when: the workflow has no workflow_dispatch trigger ... or a push would do it anyway.' The exclusion names a concrete alternative action (a push) rather than leaving routing to inference.

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