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

Goes well beyond the annotations (destructiveHint/idempotentHint). It discloses the actual consequence of mutating an active plan (it changes what every run spends), the precondition (explicit user agreement to the new estimate), and the failure mode (refused, and the estimate is returned). This is exactly the behavioral context an agent needs before a destructive mutation.

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, zero waste. The purpose and partial-update semantics come first, and the dangerous active-plan/confirm condition is front-loaded rather than buried. Nothing is repeated from the schema.

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?

With 100% schema coverage, annotations declaring destructiveness and idempotency, and no output schema to explain, the description covers everything an agent must know: what it edits, that edits are partial, and the confirm requirement for active plans. No material gap remains.

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 adds real meaning beyond the schema: the partial-update contract ('only what you pass changes') applies across all 13 params, and it reinforces the confirm gate's dependency on the user-agreed estimate. That extra semantic layer justifies a 4.

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 and resource ('Change a plan') and adds the key scope qualifier 'only what you pass changes', which frames this as a partial-update operation. It also names the sibling list_autopilot_plans as the source of planId, so the agent can place it precisely amid the autopilot create/delete/activate/run family.

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 clear context: retrieve planId from list_autopilot_plans, and if the plan is ACTIVE you must pass confirm:true after user agreement or the call is refused with the estimate. It does not explicitly name when to prefer this over create_autopilot_plan, delete_autopilot_plan, or activate_autopilot_plan, but the blocking condition is well covered.

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