Maps Agent

Search Maps Agent knowledge

search_knowledge

Read-onlyIdempotent

Search everything Maps Agent publishes about Google Maps and Google Business Profile for local businesses: answers, guides, research, glossary, blog, industry pages. Use it first for any question (getting more Google reviews, choosing a Business Profile category, a suspended profile, ranking in the map pack). Returns ranked pages with title, one-line summary, form, last-updated date and URL; read one in full with get_article.

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_knowledge"
  }
}

Input Schema

Name	Required	Description
`form`	No	Only this form. answer = one question answered first; guide = long reads, troubleshooting and copyable templates; research = our own measurements and statistics with method; glossary = terms; blog = articles; industry = what changes trade by trade; comparison = Maps Agent against other options; changelog = dated Google Business Profile changes.
`limit`	No	How many results (default 8, at most 25).
`query`	Yes	The question or keywords in plain English, e.g. 'how to get more Google reviews'.

Output Schema

Name	Required	Description	Default
`query`	Yes
`results`	Yes	Best match first.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 9, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "query": {
+      "type": "string"
+    },
+    "results": {
+      "description": "Best match first.",
+      "items": {
+        "properties": {
+          "form": {
+            "description": "The page's form.",
+            "enum": [
+              "answer",
+              "guide",
+              "research",
+              "glossary",
+              "blog",
+              "industry",
+              "comparison",
+              "changelog",
+              "page"
+            ],
+            "type": "string"
+          },
+          "slug": {
+            "description": "Its slug inside the form.",
+            "type": "string"
+          },
+          "summary": {
+            "description": "One or two plain sentences: the page's description or opening.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "title": {
+            "description": "The page title.",
+            "type": "string"
+          },
+          "topic": {
+            "description": "Grouping inside the form: answer cluster, guide kind, trade, blog vertical.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "updated": {
+            "description": "The page's own last-updated day, YYYY-MM-DD.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "description": "The page on maps-agent.com — cite it.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "form",
+          "slug",
+          "title",
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "query",
+    "results"
+  ],
+  "type": "object"
+}

First observedNov 9, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered; the description adds that results are ranked and carry title, summary, form, last-updated date and URL. It does not discuss pagination or what happens when nothing matches, leaving a small gap beyond the strong 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.

Conciseness5/5

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

Two dense sentences with the corpus scope front-loaded, then usage guidance, then the handoff to get_article. No redundant restatement of the title or annotations.

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?

With a full output schema and complete annotations, the description only needs to convey scope, entry-point role and the follow-up path, all of which it does. Nothing an agent needs in order to call it correctly is missing.

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 coverage is 100% and the form enum is documented in detail in the schema itself, so the description's only param-adjacent content is a query example under usage guidance. Baseline 3 applies since the schema carries the parameter burden.

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?

Opens with a specific verb and precisely scoped resource ('Search everything Maps Agent publishes about Google Maps and Google Business Profile'), then enumerates the content types covered (answers, guides, research, glossary, blog, industry pages). An agent can immediately distinguish this broad search from siblings like get_article or list_articles.

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?

Explicitly states 'Use it first for any question' and gives concrete question shapes (getting more reviews, choosing a category, a suspended profile, map pack ranking), establishing it as the default entry point. It also names the follow-up alternative: read a result in full with get_article.

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

All Maps Agent tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.