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

The description adds meaningful behavioral context beyond annotations: it returns a draft for human review (not a final deliverable), uses only buyer-supplied information, performs no outbound actions, and has a price of 0.25 USD requiring explicit wallet authorization. This is valuable for an agent deciding whether to invoke the tool. The annotations (destructiveHint=true) are not contradicted; the description's 'draft for human review' implies non-destructive output, but the annotation may refer to payment side effects, which the description discloses.

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?

Four sentences, each carrying distinct information: what it produces, input constraints, output nature, and cost/payment requirement. No filler or repetition. The most important information (what it does) is front-loaded.

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?

The description covers the core behavior, constraints, and payment, but with no output schema and 5 parameters (including payment_signature and result_signature), an agent might need more detail on how to provide the payment signature or what the result signature means. The nested 'input' object is partially explained, but the auxiliary parameters are not. For a paid tool with destructiveHint=true, this is a moderate 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 0%, so the description must compensate. It mentions 'supplied goals' which maps to the 'brief' parameter, and 'buyer-supplied information' maps to 'source_text', but it doesn't explain 'audience', 'result_expires', 'idempotency_key', 'result_signature', or 'payment_signature'. The description adds some context for the main inputs but leaves the payment/result parameters unexplained, which is a gap given zero schema coverage.

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 states a specific verb ('Turn supplied goals into...') and resource (customer success plan), listing concrete outputs: onboarding milestones, adoption actions, ownership, measurable outcomes. It distinguishes itself from siblings like account_plan by focusing on customer success/onboarding, though it doesn't explicitly name a sibling.

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 description clearly states the input source ('buyer-supplied information only') and constraints ('no external research or outbound actions'), which tells the agent when this tool is appropriate. It doesn't explicitly name alternatives or exclusions, but the constraints imply when not to use it (e.g., when external research is needed).

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