List the available values for one taxonomy kind across the corpus: persona, route, domain, condition, or age-band. Use this to discover what can be passed to topic.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | Yes | Taxonomy kind to enumerate. |
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | Sanitised jsonb projection from the locked ask_* RPC layer. | |
| tool | Yes | ||
| source | Yes | ||
| disclaimer | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds scope context ('across the corpus') but doesn't contradict annotations.
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, each serving a clear purpose. First sentence states action and scope; second sentence gives usage guidance. No wasted words.
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?
Simple tool with one enum param and output schema. Description fully covers purpose, scope, and utility. No gaps given the tool's simplicity.
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 describes 'Taxonomy kind to enumerate' with enum values. Description adds that these values can be passed to `topic`, providing critical usage context beyond 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?
Specifically says 'list the available values for one taxonomy kind' and enumerates the kinds. Distinguishes from sibling 'topic' by noting that output can be passed to it.
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?
Explicitly states 'Use this to discover what can be passed to `topic`.' Clear context, but no mention of when not to use or alternatives.
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 has a clearly distinct purpose: browse discovers taxonomy values, topic retrieves content for a value, compare does side-by-side analysis, fetch gets full answers, etc. No two tools overlap in functionality, and descriptions make their unique roles evident.
All tool names are lowercase, using underscores for compound names (lookup_code, red_flags) while others are single words. This pattern is consistent and predictable, with no mixing of conventions like camelCase.
With 11 tools covering search, retrieval, browsing, comparison, milestones, pathways, red flags, clinical code lookup, and a home overview, the count is well-scoped for a knowledge corpus. Each tool serves a necessary function without redundancy.
The tool surface covers the full user journey: orienting (home), discovering (browse), searching (search), retrieving (fetch), comparing (compare), exploring (topic, milestones, pathway, red_flags, related), and code-based lookup (lookup_code). No critical missing operations.
