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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: it discloses exactly what is returned (plain text with [brackets] for missing values, tips, and No Surprises Act / Good Faith Estimate rights with CMS links) and closes with 'It never sends anything', which is a valuable reinforcement of the read-only contract.

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 key fact — draft a letter, never sent — leads the description, and the second sentence earns its length by covering both trigger examples and return content. It is slightly dense but has no filler sentences.

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 13-parameter generator with no output schema, the description covers the essentials: what it produces, how placeholders are marked, and that it is non-sending. The remaining detail (benchmark computation, enum behaviors) lives in a fully annotated schema, so nothing critical is missing.

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 100% across 13 parameters, and the enum values, units, and conditional logic (e.g. code+amount adds the Medicare benchmark, billed_by defaults to comparing both) are all documented in the schema itself. The description maps user phrasings to the four 'type' values but adds nothing beyond what the schema already states, so the baseline of 3 applies.

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 names a specific verb and resource ('Draft a letter to a billing office') and grounds it in four concrete user intents ('help me dispute this bill', 'write a letter asking for an itemized bill', etc.). None of the siblings (check_price, check_whole_bill, look_up_hospital, search_services) generate letters, so the boundary is unambiguous.

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 quoted request examples make the triggering condition clear — the tool is for users who want to communicate with a billing office rather than look up prices or bills. It stops short of explicitly naming when to prefer a sibling or what to do if the request is purely informational, so it is strong context without formal exclusions.

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