search「全国企業データベース-プレスリリース配信サービス」（companydata.tsujigawa.com）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。全国企業データベース-プレスリリース配信サービス 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。
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | 探したい言葉（例: 料金 支払い方法） |
| Name | Required | Description | Default |
|---|---|---|---|
| results | Yes | ||
| candidates | No |
Changes observed during successful MCP inspections.
Output schema / properties / candidatesAdded value: +{
+ "items": {
+ "properties": {
+ "id": {
+ "type": "string"
+ },
+ "title": {
+ "type": "string"
+ },
+ "url": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "id",
+ "title",
+ "url"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, non-destructive, closed-world behavior. The description adds useful behavioral context: that it only searches already-loaded pages (not live web) and that stale content is possible after loading. It doesn't cover rate limits or pagination, but this is a minor gap given annotation coverage.
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?
The description is a single dense paragraph that front-loads the purpose, scope, and usage instructions. It is efficient, but slightly long and could be broken with line breaks for readability.
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?
Given the simple one-parameter tool, the description covers purpose, scope limitations, fallback strategies, and behavior on no results. Output schema exists, so return format need not be explained. It is complete for correct invocation.
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%, so the single query parameter is fully documented with a description and example. The description adds no format or syntax details beyond the schema; baseline 3 applies.
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 (探し/検索) and resource (loaded pages from a specific site), and specifies that results are excerpts with URLs. It distinguishes itself from siblings like fetch and list_pages by describing its keyword-based search scope.
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 says to use this first when asked about the site, explains the scope limitation (only loaded pages, not the whole web or post-load updates), and instructs how to retry with synonyms. It also tells the agent to check candidate pages if no results, and to avoid guessing if still none.
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.