Skip to main content
Glama

hou_tea_discover_extended

Unlock additional tea tools for comparison, health filtering, and agent cards when core tools are not enough.

Instructions

[meta] Reveal extended tools (compare / health-filter / agent-card) by adding them to tools/list. Optionally filter by groups or specific tools. Call this when the core 6 tools aren't enough for the user's intent. Idempotent.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
groupsNoReveal all tools in these groups. Default: ['extended'].
toolsNoReveal a specific subset of extended tools by name.

Implementation Reference

  • The tool `hou_tea_discover_extended` is defined as a meta-tool (not in the registry). It is defined inline with name, description, and inputSchema (accepting optional `groups` and `tools` arrays).
    const DISCOVERY_TOOL_NAME = "hou_tea_discover_extended";
    const DISCOVERY_TOOL = {
      name: DISCOVERY_TOOL_NAME,
      description:
        "[meta] Reveal extended tools (compare / health-filter / agent-card) by adding them to tools/list. Optionally filter by `groups` or specific `tools`. Call this when the core 6 tools aren't enough for the user's intent. Idempotent.",
      inputSchema: {
        type: "object" as const,
        properties: {
          groups: {
            type: "array",
            items: { type: "string", enum: ["extended"] },
            description: "Reveal all tools in these groups. Default: ['extended'].",
          },
          tools: {
            type: "array",
            items: { type: "string" },
            description: "Reveal a specific subset of extended tools by name.",
          },
        },
        additionalProperties: false,
      },
    };
  • The `handleDiscover` function is the actual handler/executor for `hou_tea_discover_extended`. It reveals extended tools by adding them to the `revealedExtended` Set, sends a tool list changed notification, and returns the list of revealed/available extended tools.
    async function handleDiscover(args: Record<string, unknown>) {
      const ctx = startCall(DISCOVERY_TOOL_NAME);
      const groups = Array.isArray(args.groups) ? (args.groups as string[]) : ["extended"];
      const explicit = Array.isArray(args.tools) ? (args.tools as string[]) : undefined;
    
      const before = new Set(revealedExtended);
      if (groups.includes("extended")) {
        if (explicit && explicit.length > 0) {
          for (const n of explicit) {
            if (EXTENDED_TOOL_NAMES.has(n)) revealedExtended.add(n);
          }
        } else {
          for (const n of EXTENDED_TOOL_NAMES) revealedExtended.add(n);
        }
      }
      const newlyRevealed = [...revealedExtended].filter((n) => !before.has(n));
    
      // Notify any listening MCP clients that the tool list changed.
      if (newlyRevealed.length > 0) {
        try {
          await server.sendToolListChanged();
        } catch {
          // notification is best-effort; older clients may not subscribe.
        }
      }
    
      return jsonResult(
        wrapOk(
          ctx,
          {
            revealed: [...revealedExtended],
            newly_revealed: newlyRevealed,
            available_extended: extendedSummary(),
          },
          newlyRevealed.length > 0
            ? [
                {
                  tool: "tools/list",
                  reason: "Re-list tools to see the newly revealed extended tools.",
                },
              ]
            : undefined
        )
      );
    }
  • src/index.ts:91-93 (registration)
    The `listTools` function includes `DISCOVERY_TOOL` alongside core + revealed extended tools, registering the discovery tool in the MCP tools/list response.
    function listTools() {
      return [...listForMcp(revealedExtended), DISCOVERY_TOOL];
    }
  • src/index.ts:183-185 (registration)
    The CallToolRequestSchema handler routes calls with name === DISCOVERY_TOOL_NAME to `handleDiscover`, effectively registering the tool for invocation.
    if (name === DISCOVERY_TOOL_NAME) {
      return handleDiscover(args);
    }
  • The `EXTENDED_TOOLS` array (and `EXTENDED_TOOL_NAMES` set) defines the extended tools that `hou_tea_discover_extended` can reveal (compare, filter_by_health, agent_card).
    const EXTENDED_TOOLS: ToolDef[] = [
      {
        name: "hou_tea_compare",
        group: "extended",
        summary: "Side-by-side compare 2–4 products.",
        description:
          "Compare 2–4 products across sensory profile, price, brewing difficulty, season, and use-case. Use when the user is choosing between specific candidates.",
        inputSchema: obj(
          {
            skill_ids: {
              type: "array",
              items: { type: "string" },
              minItems: 2,
              maxItems: 4,
              uniqueItems: true,
            },
          },
          ["skill_ids"]
        ),
        execute: (args) =>
          houTea.compare(args as unknown as Parameters<typeof houTea.compare>[0]),
      },
      {
        name: "hou_tea_filter_by_health",
        group: "extended",
        summary: "Filter teas by health constraints (pregnancy, insomnia, etc.).",
        description:
          "Filter products by health constraints. Returns only teas safe under the given conditions (e.g. avoid caffeine for insomnia or pregnancy, avoid strong tannins for sensitive stomachs).",
        inputSchema: obj(
          {
            conditions: {
              type: "array",
              items: { type: "string" },
              minItems: 1,
            },
            limit: { type: "integer", minimum: 1, maximum: 50, default: 10 },
          },
          ["conditions"]
        ),
        execute: (args) =>
          houTea.constraints(
            args as unknown as Parameters<typeof houTea.constraints>[0]
          ),
      },
      {
        name: "hou_tea_agent_card",
        group: "extended",
        summary: "Capability descriptor (/.well-known/agent) — diagnostics.",
        description:
          "Fetch the full hou-tea agent capability descriptor (/.well-known/agent). Useful for discovering the latest API surface, payment recipient address, and supported networks. Call this if other tools behave unexpectedly.",
        inputSchema: obj({}),
        execute: () => houTea.agentCard(),
      },
    ];
Behavior4/5

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

No annotations are provided, so the description carries full responsibility. It discloses that the tool modifies the tool list, states it is idempotent, and marks it as a meta operation. This is good but could be more detailed about side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (two sentences) and front-loaded with the key purpose. Every sentence earns its place with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (2 optional parameters, no output schema) and high schema coverage, the description covers purpose, usage scenario, behavior (idempotent), and parameter filtering options. It is complete for the intended use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% as both parameters have descriptions. The tool description adds 'Optionally filter by groups or specific tools,' which mostly restates the schema. Baseline 3 is appropriate since no significant extra meaning is added.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Reveal extended tools' and provides specific examples (compare / health-filter / agent-card). It explicitly distinguishes from the 'core 6 tools' mentioned, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes a clear usage trigger: 'Call this when the core 6 tools aren't enough for the user's intent.' It does not explicitly mention when not to use it, but the context is sufficient for an agent to decide appropriately.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jackrain19743/hou-tea-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server