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

Annotations only say readOnlyHint=false and destructiveHint=true; the description adds real behavior beyond that — that this is an asynchronous start-pricing call whose result must be polled via get_quote until status is complete, and that disclosures are a hard precondition to any purchase. It still omits what happens to abandoned quotes, whether duplicate calls are deduplicated (the idempotency_key semantics live only in the schema), and any error paths such as line_not_available.

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?

The first two sentences are excellent and front-loaded, but roughly two-thirds of the text is a verbatim verbatim disclosure list (eleven bullets) that serves the purchase step more than this call, and it repeats overlapping home/auto variants. The instruction to show disclosures word for word arguably justifies including them, but the result is bulky relative to the tool-specific guidance.

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 nested, three-product-line creation call with no output schema, the description covers the intake flow, the post-call polling step, and the pre-purchase disclosure obligation, which is most of what an agent needs. It does not cover failure modes (409 line_not_available, 422 home_premium_above_maximum) that appear only in schema descriptions, nor quote expiration.

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 43%, so the description must compensate. It does clarify that insured.email identifies the consumer and that read_declarations_page output should be passed in, but it never mentions partner_ref, referral_token, idempotency_key, or the required shape of the auto/policy blocks, leaving several parameters to the schema alone.

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 ('Start pricing a Premium Lock quote'), names the exact field that identifies the consumer ('insured.email'), and distinguishes itself from the sibling get_quote by declaring that create_quote returns a quote_id to be polled. An agent can tell what this does and where it sits in the flow without opening the schema.

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 gathering order: first ask for the email, then hunt for a declarations page and route it to read_declarations_page, and only fall back to asking the consumer for fields if none is found. It also names the prerequisite gate ('Before any purchase, show the consumer every disclosure... word for word') and the sibling to poll afterwards.

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