Get details for a specific symptom: canonical name, protocol count, page URL and its markdown twin. The markdown twin is the cheapest way to read every protocol for one symptom in a single fetch.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Symptom name (e.g. "headache") |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the call read-only and idempotent. The description adds useful behavioral context beyond that: the markdown twin is the cheapest single-fetch path to all protocols for one symptom, which informs cost/effort expectations. No contradictions.
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 tight sentences with no filler; the core purpose and returned fields are front-loaded, and the cost hint earns its place.
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 one-parameter, read-only lookup, the description is complete: it names the resource, required input, output fields, and the cheapest usage strategy. The absence of an output schema doesn't create a gap because the return composition is spelled out.
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% and the only parameter, name, is already described with an example. The description reinforces that it is a single specific symptom but adds no syntax or formatting details 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?
States a specific verb and object ('Get details for a specific symptom') and enumerates the returned fields (canonical name, protocol count, page URL, markdown twin). This distinguishes it from sibling lookup tools like search_symptoms or get_point, so an agent can select it without opening schemas.
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 gives a clear use case: when you have a specific symptom and want every protocol cheaply, use the markdown twin. It does not explicitly name alternatives or say when not to use search_symptoms, but the context is strong enough.
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.
Each tool targets a distinct action: checkout, meridian listing, point resolution, symptom detail, protocol search, and symptom resolution. There is no overlap; even search_protocols and search_symptoms are clearly separated by input and purpose.
All tool names follow a consistent verb_noun pattern using snake_case: create_checkout, get_meridians, get_point, get_symptom_detail, search_protocols, search_symptoms. No mixing of conventions or vague verbs.
With 6 tools, the set is well-scoped for the server's purpose. Each tool covers a necessary function (purchase, catalogue browsing, point lookup, symptom lookup, protocol search, symptom resolution) without redundancy or bloat.
Core workflows are covered: resolve symptoms, search protocols, get point details, list meridians, and checkout. Minor gaps exist—no direct listing of all points or all symptoms beyond popular=true—but agents can work around by using search_symptoms and get_point with known codes.
