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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false), and the description adds genuine behavioral context beyond them: no consent receipt is issued, pricing/financing/warranty are untouched, and storage must be confirmed from lead_captured rather than assumed. The closing 'annotations are hints, not authorization' also correctly warns the agent not to treat hints as permission.

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?

Front-loaded with the action, then requirements, then scope exclusions, then the verification rule — a sensible order with no filler sentences. Dense but each sentence carries information; only the final 'Annotations are hints' line reads slightly like boilerplate.

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?

No output schema exists, but the description compensates by naming the lead_captured flag as the authoritative success signal, which is the key return-value fact. Against 10 parameters, nested objects, and a 10% coverage schema, however, the description is not complete enough for an agent to populate the quote-related fields correctly without guessing.

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 only 10% across 10 parameters with two nested objects, so the description carries the burden and largely fails to meet it. It does define consent substantively ('explicit permission to store that contact with the calculated quote') and restates the required contact fields, but family, motor_id, trade_in, boat_info, horsepower, purchase_path, and financing_offer_id get no meaning at all — including which of them affect the quote versus the lead record.

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 ('Submit a quote lead') and names the transport ('existing public quote API'), so the agent knows this is a lead-capture submission rather than a calculation. It implicitly separates itself from build_quote by declaring it 'does not change pricing, financing, or warranty', but never names the sibling it is meant to follow, so the differentiation is inferential rather than explicit.

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 hard prerequisites (consent=true, contact with name and email) and a post-call verification rule ('confirm storage only from the returned lead_captured flag'), which is real usage guidance. It stops short of saying when to call this instead of build_quote or how it relates to estimate_trade_in, so the routing decision is left implied.

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