v1_icd10ICD-10-CM search: Search ICD-10-CM diagnosis codes by term or code. Source: NLM Clinical Tables. $0.008 per call · GET /v1/icd10
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Search text. Example: 'type 2 diabetes'. | |
| code | No | Code prefix (alternative). Example: 'E11'. | |
| maxList | No | Max results 1-50. Example: '10'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful context: NLM as the source, per-call cost, and the HTTP method. It does not disclose output format, pagination behavior, or whether at least one of q/code is effectively required despite the schema marking all params optional.
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 compact and front-loaded with the core action. The only minor redundancy is the 'ICD-10-CM search:' prefix, which restates the title, but the rest of the sentence earns its place by adding source, pricing, and method.
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 simple read-only lookup with three optional, well-documented parameters, the description is mostly complete. The lack of an output schema means a brief note on return value shape would improve completeness, but the low complexity and strong schema coverage offset that 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?
The input schema has 100% parameter description coverage, so the schema already explains q, code, and maxList with examples. The description's phrase 'by term or code' adds mild reinforcement but not significant new 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 states a specific verb ('Search'), a specific resource ('ICD-10-CM diagnosis codes'), and the two supported access modes ('by term or code'). This clearly distinguishes the tool from the many other domain-specific sibling lookup tools.
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?
No guidance is given about when to prefer this tool over alternatives, nor are any exclusions or prerequisites mentioned. The intended use is only implied by the domain name and search language, not explicitly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Every tool targets a distinct resource or operation—geocoding, weather, DNS, VIN, stock quotes, etc.—with no meaningful overlap in purpose. Even the location- and finance-related tools are clearly separated by their descriptions.
All tools follow the same v1_<resource>[_modifier] snake_case pattern, such as v1_air_quality, v1_reverse_geocode, and v1_validate_email. Although the names are not verb-based, the convention is perfectly consistent across all 31 tools.
31 tools exceeds the 25+ threshold and creates a heavy selection burden for agents, even though the server's stated purpose is broad. Many endpoints are small single-purpose lookups that could be grouped into fewer combined tools without losing clarity.
As a general public-data utility, the set covers a wide range of common lookup categories: location, weather, finance, legal, health, business, internet, and reference data. It has minor gaps like historical financial time series or phone-number validation, but no obvious dead ends since all tools are self-contained read-only lookups.