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

Annotations only say readOnlyHint=false, openWorldHint=true, destructiveHint=false; the description goes well beyond that, disclosing post-call behavior ('a licensed agent replies', 'nothing is bound and no price is given', 'returns a reference number') and the consent precondition for contacting the agency. This is meaningful outcome information an agent cannot get from 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?

Front-loaded with the core action and return behavior in the first two sentences, with the safety constraints after. The one-agency prohibition is restated twice ('never call this for every agency...' and 'If they ask to send to all of them, do not call it'), which is slight redundancy, though defensible given the criticality of the constraint.

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, and the description covers the essential return ('a reference number') plus the downstream consequence of the request. For a 9-parameter, 6-required tool, it is nearly complete, though the 'business' parameter and failure/duplicate-submission behavior remain unaddressed.

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 only 44% schema description coverage, the description compensates by naming the needed inputs (name, email or phone, line, state, coverage details) and clarifying the email-or-phone alternative, which the schema does not express since neither is marked required. It still says nothing about the 'business' parameter or why agency is bound to the find_agencies value beyond what the schema already states.

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 ('Send an insurance quote request') and scopes it precisely to 'the one agency the person chose by name from find_agencies', explicitly linking to the sibling tool that produces that value. An agent can immediately tell this apart from find_agencies or search_servers.

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 explicit when and when-not guidance: one agency per request, never batch, never pick an agency for the user. It even prescribes the fallback behavior ('show the list and ask which one agency they want') when the user asks to send to all, which is exactly the routing decision an agent needs.

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