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

Annotations already flag destructiveHint=true, idempotentHint=true, and openWorldHint=true, but the description adds the crucial business behavior: the operation consumes AI credits on each run and is gated by an explicit user consent step, with a refusal path that returns the estimate. That is real added context beyond the structured hints, though it does not describe post-activation state or scheduling failure modes.

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 sentences: the action and its cost side effect first, the gating requirement second. No filler, no restatement of the title.

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 write tool with no output schema, the description supplies the cost implication, the consent gate, and the refusal response, which is what an agent needs to avoid calling it prematurely. Minor gaps remain about what the returned estimate/confirmation looks like and any rate limits.

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%, so the baseline is 3, but the description goes further by explaining the failure semantics of confirm (request is refused with the estimate when absent) rather than merely restating the schema's 'true ONLY after the user agreed' wording. planId, workspaceId, and idempotencyKey are left entirely to the schema.

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 concrete verb+resource ('turn a plan on so it runs on its schedule') and the consequence ('spends AI credits on every run'), which cleanly separates it from deactivate_autopilot_plan, update_autopilot_plan, and create_autopilot_plan in the sibling list.

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?

Gives the exact precondition for the required confirm flag ('after the user agreed to the estimated credits per run') and the outcome of omitting it ('refused with the estimate'). It does not name the sibling to use for the opposite action, but the paired names make that inferable.

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