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

The description usefully flags the two-phase preview/execute gate, which the readOnlyHint=false annotation alone would not convey. But the substantive behavior of a trigger tool is undisclosed: whether the run is async, whether it creates a pending run that must be approved (as the approve/reject_ai_run siblings suggest), and whether it consumes credits or overwrites an existing plan.

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 short sentences, action first and the confirm caveat second, with no filler. Every clause carries information.

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 2-param mutation with no output schema, the description covers what and the safety gate but not what happens after execution — where the generated run lands and whether follow-up approval is required. In an ecosystem with approve_ai_run and list_ai_runs_awaiting_review, that missing link is the main gap.

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 both parameters are fully documented upstream and the baseline is 3. The description adds only the soft constraint that clientId should reference an AI-coached client, with no added syntax or format detail.

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?

"Kick off a fresh AI plan generation for one of the coach's AI-coached clients" states a specific verb (kick off), resource (AI plan generation) and scope (AI-coached clients), which separates it from approve_ai_run or requeue_ai_run. It stops short of naming a sibling explicitly, so an agent still has to infer the boundary with the other AI-run tools.

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 confirm-gate note tells the agent to expect a preview first, and "AI-coached clients" implies a precondition. However, nothing says when to call this versus requeue_ai_run, approve_ai_run, or offer_ai_coach_to_client, so the routing decision among four adjacent AI tools is left to inference.

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