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

There are no annotations, so the description carries the full burden, and it does this exceptionally well. It discloses exact sentinel behaviors for facility-only codes (not_applicable_in_this_setting), non-payable PFS statuses (not_payable_under_pfs), contractor-specific coverage, and the rule that a missing national rate is never treated as non-coverage. It also clarifies the amount is clinician fee only, excluding facility, device, or imaging fees.

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 main contract is front-loaded in the first sentence, and every subsequent sentence adds meaningful edge-case behavior rather than filler. The description is dense but still readable, and all distinctions—setting, PFS status, contractor specificity, fee scope—are explicitly justified.

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?

Given no output schema and no annotations, the description thoroughly covers what the agent can expect back: article-level coverage data, ICD-10 lists, national PFS amounts, and special sentinel values. It also prevents common misinterpretations such as treating a missing national rate as non-coverage or treating the output as clinical guidance.

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 for both parameters is 100%, so threed description is at baseline 3. It confirms `codes` means one or more CPT/HCPCS codes and that `diagnosis` is the ICD-10 value used for coverage matching, but this largely restates the schema descriptions. The additional detail about setting and PFS statuses pertains to return behavior rather than new parameter semantics.

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 ('report') and a precise resource: CMS Local Coverage Articles and the CMS Physician Fee Schedule PROFESSIONAL amount for given diagnosis and CPT/HCPCS codes. It clearly differentiates the tool's scope by specifying covered/non-covered ICD-10 diagnoses and fee-schedule payment status.

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 the tool is applicable: for a diagnosis plus one or more CPT/HCPCS codes, and explicitly states what the tool is NOT for ('does NOT compare clinical effectiveness or recommend treatment'). No sibling tools exist, so it cannot name alternatives, but the boundary is nevertheless explicit enough for an agent to select it appropriately.

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