Skip to main content
Glama
zizzfizzix

Bing Webmaster Tools MCP Server

by zizzfizzix
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

get_related_keywords

Get related keyword impressions for a base query by specifying country, language, and date range. Use pagination to retrieve up to 500 rows of keyword data.

Instructions

Get keyword impressions for related keywords in the selected period.

Args: query: The base keyword query country: The country code language: The language code start_date: The start date of the period end_date: The end date of the period

Returns: List[Keyword]: List of related keywords and their impression data

Raises: BingWebmasterError: If related keywords cannot be retrieved

Returns at most limit rows (default 50, max 500). When the result reports a next_offset, call again with offset=next_offset to get more rows.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of rows to return.
queryYes
offsetNoIndex of the first row.
countryYes
end_dateYes
languageYes
start_dateYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.2.0
    • addedInput schema / properties / limit
      Added value: +{
+  "default": 50,
+  "description": "Maximum number of rows to return.",
+  "maximum": 500,
+  "minimum": 1,
+  "title": "Limit",
+  "type": "integer"
+}
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Index of the first row.",
+  "minimum": 0,
+  "title": "Offset",
+  "type": "integer"
+}
    • removedInput schema / properties / self
      Removed value: -{
-  "title": "self",
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "self",
-  "query",
-  "country",
-  "language",
-  "start_date",
-  "end_date"
-]New value: +[
+  "query",
+  "country",
+  "language",
+  "start_date",
+  "end_date"
+]
  2. Changed1 schema field changedv1.0.0
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$defs": {
+    "Keyword": {
+      "properties": {
+        "BroadImpressions": {
+          "title": "Broadimpressions",
+          "type": "integer"
+        },
+        "Impressions": {
+          "title": "Impressions",
+          "type": "integer"
+        },
+        "Query": {
+          "title": "Query",
+          "type": "string"
+        },
+        "__type": {
+          "title": "Type",
+          "type": "string"
+        }
+      },
+      "required": [
+        "__type",
+        "BroadImpressions",
+        "Impressions",
+        "Query"
+      ],
+      "title": "Keyword",
+      "type": "object"
+    }
+  },
+  "properties": {
+    "result": {
+      "items": {
+        "$ref": "#/$defs/Keyword"
+      },
+      "title": "Result",
+      "type": "array"
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "title": "get_related_keywordsOutput",
+  "type": "object"
+}
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden. It discloses pagination behavior (limit, offset, next_offset), maximum rows, and error raising (BingWebmasterError). It does not mention side effects (none expected) or authentication requirements, but it covers the key operational aspects for a read tool.

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 well-organized with a one-sentence purpose, followed by Args, Returns, Raises, and pagination notes. Each line is concise and actionable, with no redundant or verbose content. It is front-loaded with the core purpose and fits naturally in the structure.

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

Completeness4/5

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

For a tool with 7 parameters and an output schema, the description covers the purpose, parameter meaning (though brief), return type, error handling, and pagination. It does not elaborate on what 'related keywords' means or how impressions are computed, but these are likely domain-specific and covered by the output schema. Overall, it provides enough context to invoke 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?

Schema description coverage is only 29% (limit and offset only). The description's Args section adds brief but meaningful explanations for all five required parameters (query, country, language, start_date, end_date), such as 'country code' and 'language code'. It also explains the pagination parameters in the text, compensating for the missing schema descriptions.

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 verb (Get), the resource (keyword impressions for related keywords), and the time constraint (selected period). It distinguishes itself from siblings like get_keyword (which targets a single keyword) and get_keyword_stats (likely stats for an exact keyword) by emphasizing 'related keywords'.

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

Usage Guidelines3/5

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

The description implies usage for retrieving related keyword impressions, but it does not explicitly state when to use this tool over alternatives such as get_keyword or get_keyword_stats, nor does it mention any when-not-to-use conditions. It relies on the name and a general sense of the operation.

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

Deploy Server

Other Tools