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

Annotations declare destructive=true but say nothing about cost; the description supplies the crucial behavioral fact that this holds and spends the account's minutes, that the render is queued rather than immediate, and that it acts as a consent gate on the user's behalf. That is material context an agent cannot get from the structured fields.

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?

Cost and the consent precondition are front-loaded, which is the right ordering for a destructive call. There is mild redundancy between "only after the user has seen the storyboard and agreed" and "Do not approve on the user's behalf," but the reinforcement is defensible for a destructive action.

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 no output schema, the description still conveys the outcome (minutes held, render queued) that would otherwise be missing. The only gap is that it doesn't say what is returned on approval (e.g. a render/job identifier) or what to do if the balance is insufficient, but the critical decision inputs are covered.

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?

There is only one parameter (`id`, a UUID) and schema coverage is 100%, so the schema already does the work. The description never clarifies what the id identifies (presumably the storyboard/lesson) or whether an unapproved lesson id is rejected — baseline 3 for a fully documented single parameter.

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+resource ("Approve the storyboard and start rendering") and adds a unique differentiator — "the only call that spends the account's minutes" — that no sibling shares. An agent can immediately distinguish it from get_usage or create_lesson.

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 an explicit precondition ("Use only after the user has seen the storyboard and agreed"), a negative case ("Do not approve on the user's behalf without their go-ahead"), and routes to a named sibling ("Check get_usage first if the balance may be tight"). When, when-not and alternative are all present.

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