Create Pipeline

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, and the description does not contradict them. It adds a genuinely useful mechanic — params_json entries are passed as keyword arguments and some operations auto-build a single typed model from those kwargs — but says nothing about auth/permission requirements, that creating a pipeline actually enqueues CI jobs, or that repeat calls create duplicates (consistent with non-idempotent but not explained).

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 operation name is front-loaded and the text is short overall. However, roughly half the content is family-level boilerplate enumerating capabilities unrelated to creating a pipeline, which is wasted space for an agent trying to call this tool correctly.

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 free-form JSON-string parameter with no enum, no nested schema, and no output schema, the description is the only place the expected payload shape could be documented — and it isn't. Nothing tells the agent which kwargs create_pipeline accepts or what a successful response contains, so a correct first call is largely guesswork.

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%, but the sole parameter's schema text ('JSON string of parameters to pass to the action') is nearly content-free. The description partially compensates by explaining that the JSON keys become keyword arguments to the named operation and that typed-model operations are built automatically. It still never names the keys this operation requires (e.g. project path, ref), leaving the agent to guess the payload shape.

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 body describes a generic family behavior ('Run a typed GitLab GraphQL operation by name'), and the only indication of what this specific tool does is the title 'Create Pipeline' restated at the start. It never states what creating a pipeline means here — which project, which ref, what triggers — so the agent must infer the operation name from the tool name.

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?

It gives a real routing rule against the REST siblings ('prefer it for GraphQL-only capabilities ... and rich nested reads'), which is useful context. But the enumerated GraphQL-only capabilities (merge-request update/delete, pipeline retry/cancel, member ops) do not include pipeline creation, so it's unclear whether create_pipeline should be preferred over gitlab_run_pipeline or gitlab_create_pipeline_schedule.

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