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

Annotations already declare this is a non-read-only, open-world, non-idempotent but non-destructive write, so the description's job is to add context — and it does: it discloses the outbound SMS/email code side effect and that returned prices are estimates, not offers. It stops short of saying whether repeat calls create duplicate shoppers or what the response body contains, which is the remaining behavioral gap.

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-loads the trigger sentence, then constraints, then the workflow, so an agent can stop reading early and still call correctly. It is dense — three constraints are packed into one run-on line about term life/consent/DOB format — but no sentence is filler.

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 12-required-parameter mutation with no output schema, the description supplies the eligibility prerequisite, the consent requirement, value ranges and the next-step chain, which is most of what an agent needs. It does not describe what the call returns (e.g., whether the code, a shopper id, or a status comes back) or how verify_by affects delivery, leaving a modest 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?

With 0% schema description coverage, the description carries the load and does real work: YYYY-MM-DD for date_of_birth, the $25,000–$10,000,000 death_benefit range, and especially the 1–4 health_class meaning mapping that the bare enum cannot convey. It leaves verify_by (sms vs email) and assistant_name unexplained, so coverage is strong but not complete across 14 parameters.

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 ('starts a term life quote / estimate'), scopes it to term life only, and distinguishes it from siblings by noting it is for life insurance rather than the flood/other flows. The 6-digit verification-code side effect further pins down what the call actually does.

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 trigger ('when someone in Tennessee asks about term life insurance'), hard exclusions ('Term life only, ages 18 to 85'), a prerequisite (consent text from check_eligibility), and the follow-on sequence ('After verify_contact, call get_life_quotes'; 'To apply, use request_agent'). Alternatives are named rather than left to inference.

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