Skip to main content
Glama

株式会社グローニティ

サイトの中を探す

search
Read-only

「株式会社グローニティ」(grownity.co.jp)から読み込んだページの中を言葉で探し、当てはまる箇所を抜粋と URL つきで返します。株式会社グローニティ について質問されたら、まずこれを使ってください。探せるのは読み込んだページだけで、ネット全体や、読み込んだあとの更新は含みません。見つからないときは、略語を正式な名前にする、同じ意味の別の言葉にするなど、言い方を変えて探し直してください。それでも見つからないときに返るページの候補も読み、それでも見つからなければ推測で答えず、このサイトの中では見つけられなかったと伝えてください。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes探したい言葉(例: 料金 支払い方法)

Output Schema

NameRequiredDescriptionDefault
resultsYes
candidatesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly, non-destructive, and closed-world, and the description reinforces the closed-world scope while adding behavior they don't cover: the index is a snapshot frozen at load time, and a failed match returns candidate pages worth reading. The no-guessing fallback instruction is genuine operational context rather than a restatement of annotations.

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

Conciseness4/5

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

Purpose and corpus scope come first, followed by when-to-use and the failure-handling ladder, so it is well front-loaded with no filler sentences. It is on the longer side, but each sentence introduces a distinct constraint or action that an agent could not infer otherwise.

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?

An output schema covers the return shape, so the description doesn't need to explain fields, and it instead spends its space on corpus limits, trigger conditions, and empty-result behavior. For a single-parameter search tool this leaves nothing an agent would need in order to call it correctly.

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

Parameters4/5

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

There is a single required parameter at 100% schema coverage, so the schema carries the baseline. The description still adds query-formulation strategy — that terms should be reworded, abbreviations expanded, and synonyms substituted on empty results — which is meaningfully more than the schema's example value.

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

Purpose4/5

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

The description names a specific verb and resource: searching pages loaded from grownity.co.jp and returning matching passages with excerpts and URLs. It also bounds the corpus (only loaded pages, not the open web), which lets an agent separate it from a general fetch or overview tool. It stops short of explicitly contrasting with the sibling search_pages, whose scope is left to inference.

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

Usage Guidelines5/5

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

It gives an explicit trigger ('if asked about 株式会社グローニティ, use this first'), explicit scope exclusions (not the whole internet, not post-load updates), and a concrete recovery procedure: rephrase the query, expand abbreviations, try synonyms, then read the returned candidate pages. It even states what to do on final failure (report not-found rather than guess).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources