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

With no annotations, the description carries full burden. It discloses that the response shape varies (flat row vs. stats_by_type array) and how to differentiate them, plus the cost per call. No destructive or authentication information is needed given the tool's read-only nature.

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 description is a single verbose paragraph. It includes rhetorical questions ('Answers: what is a fair price?') which add clarity but could be trimmed. It is still effective but not maximally concise.

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?

The tool lacks an output schema, so the description must explain the return format. It does so by describing two possible response shapes. It also covers the data source and cost. Given the complexity, this is sufficient.

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 coverage is 100% for the single parameter. The description adds context by naming the billing code types (CPT/HCPCS/MS-DRG) and implying the parameter is a specific billing code, which goes slightly beyond the schema's generic 'billing code' description.

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 clearly specifies the tool retrieves national price statistics for a billing code from hospital price-transparency files, with a distinct scope (median and spread of payer-negotiated rates). It differentiates from siblings like hpt_rates_search by focusing on a single code's stats.

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 description explains when to use the tool (to determine a fair price for a procedure) and provides guidance on interpreting results (checking for stats_by_type for ambiguous codes). It does not explicitly mention when-not-to-use or alternatives, but the context is clear.

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