pipeline_run

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

With no annotations the description carries the full burden, and it does disclose non-obvious traits: asynchronous background execution and the exit-code convention (exit 2 = work/review remains). It omits side effects, idempotency of resume, and permission requirements for a tool that mutates pipeline state.

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?

Two tight sentences with the core action front-loaded and no filler. It is arguably under-sized for a 2-param, zero-coverage, annotation-free tool, which slightly undercuts 'appropriately sized'.

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?

No annotations, no output schema, and 0% schema coverage mean the description must cover parameters, side effects, and return behavior, and it covers none of them. Only the async/polling hint is provided, leaving the agent without enough to call it correctly.

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 0% and neither 'config' (required) nor 'through' (default 'preview') is explained anywhere. The description says nothing about what config contains or what stage/scope 'through' selects, so it fails to compensate for the coverage gap.

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 gives a specific verb and resource ('Start/resume stages') and adds the execution model ('as a background job'). It is clearly distinct from pipeline_status, but it never explicitly differentiates itself from the sibling pipeline_init, which an agent could easily confuse with 'run'.

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 provides useful next-step guidance ('Poll job_status; exit 2 means work/review remains'), which is implied usage. However it gives no condition for choosing this tool over pipeline_init or pipeline_status, and no prerequisites, so usage is only partially covered.

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