Fetch a procedure article with cost band, contraindications, emergency signals, FAQ, citations. When state is supplied, also returns a ranked clinic finder pre-filtered to that state.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Procedure slug (e.g. "tplo", "hemilaminectomy", "lymphoma-chop"). | |
| state | No | Optional 2-letter state slug to pre-filter the finder. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses conditional behavior (state triggers a clinic finder) and the article's contents. However, it does not explicitly state whether the tool is read-only, error behavior, or any limitations. Adequate but not rich.
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?
Two sentences, front-loaded with the main purpose. Every part is meaningful, no fluff. Excellent structure.
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 relatively simple fetch tool with two parameters, the description is complete enough: it lists the article sections and the conditional clinic finder. Minor gaps include error handling and invalid input behavior, but these are not critical for a read-only retrieval tool.
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 both parameters. The description adds meaning by explaining that providing state triggers an additional 'ranked clinic finder' sub-component, which is not fully conveyed by the schema's 'pre-filter the finder.' This adds semantic value beyond the schema.
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 identifies the tool's purpose: fetching a procedure article with specific sections (cost band, contraindications, emergency signals, FAQ, citations). It distinguishes itself from sibling tools like estimate_procedure_cost, get_clinic, and find_specialists_by_procedure by focusing on the article retrieval.
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 implies usage context: use when you need a procedure article. It mentions conditional behavior with state (clinic finder) but does not explicitly state when not to use it or mention alternatives like search_clinics. Clear context, but no exclusions.
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.
Most tools are clearly distinct, but estimate_procedure_cost and quote_for_case overlap significantly (quote_for_case without PII behaves identically to estimate_procedure_cost). Also, find_specialists_by_procedure duplicates the clinic-finder portion of get_procedure when state is supplied, though descriptions clarify the different focus.
All tool names follow a consistent verb_noun pattern with snake_case (list, get, search, estimate, quote, find). The naming is predictable and clearly indicates the action and target resource.
Eight tools is well within the ideal range for a directory service. Each tool serves a distinct purpose related to browsing procedures, specialties, clinics, or generating estimates, with no obvious bloat or redundancy.
The tool surface covers the core directory workflows: listing/retrieving procedures and specialties, searching clinics, fetching clinic details, and estimating costs. Minor gaps include lack of a direct 'list clinics by specialty' tool and no way to manage or update directory entries, but these are not critical for a read-only directory.
