Skip to main content
Glama

Bing Search

bing_search
Read-onlyIdempotent

Searches Bing web results and returns up to 20 ranked results (title, link, snippet, rank), with market (mkt or cc), safe search and coordinate (lat, lon) targeting. Use it when Bing results are wanted. It does not return page contents (use scrape_url) and does not return Google results (use google_search). A search with no matches is charged; errors are not. Required: query.

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": "bing_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoTwo-letter country code, e.g. "us" or "it"; omit for source default, mutually exclusive with mkt. No option surcharge; 5 credits per successful request.
latNoGPS latitude of the search origin in decimal degrees, e.g. "41.9028"; send with lon; omitted uses source default. No option surcharge; 5 credits per successful request.
lonNoGPS longitude of the search origin in decimal degrees, e.g. "12.4964"; send with lat; omitted uses source default. No option surcharge; 5 credits per successful request.
mktNoMarket as language-COUNTRY, e.g. "en-US" or "it-IT"; omit for source default, mutually exclusive with cc. No option surcharge; 5 credits per successful request.
countNoRequested result count, integer 1-50, e.g. 20; actual count varies, omitted uses source default. No option surcharge; 5 credits per successful request.
firstNoOne-based position of the first result, integer at least 1, e.g. 11 to start at the 11th result; default 1. No option surcharge; 5 credits per successful request.
queryYesRequired web search keywords, e.g. "what is an api"; no default. No option surcharge; 5 credits per successful request.
filtersNoOpaque Bing filters copied from a Bing search URL; omitted means no explicit filter. No option surcharge; 5 credits per successful request.
safeSearchNoAdult-content filter: Off, Moderate or Strict, e.g. "Strict"; omitted uses source default. No option surcharge; 5 credits per successful request.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • changedInput schema / properties / cc / description
      Previous value: -"Two-letter country code such as us; omit for source default, mutually exclusive with mkt. No option surcharge; 5 credits per successful request."New value: +"Two-letter country code, e.g. \"us\" or \"it\"; omit for source default, mutually exclusive with mkt. No option surcharge; 5 credits per successful request."
    • changedInput schema / properties / count / description
      Previous value: -"Requested result count, integer 1-50; actual count varies, omitted uses source default. No option surcharge; 5 credits per successful request."New value: +"Requested result count, integer 1-50, e.g. 20; actual count varies, omitted uses source default. No option surcharge; 5 credits per successful request."
    • changedInput schema / properties / first / description
      Previous value: -"Starting result position, integer at least 1; default 1. No option surcharge; 5 credits per successful request."New value: +"One-based position of the first result, integer at least 1, e.g. 11 to start at the 11th result; default 1. No option surcharge; 5 credits per successful request."
    • changedInput schema / properties / lat / description
      Previous value: -"GPS latitude for search origin; omitted uses source default. No option surcharge; 5 credits per successful request."New value: +"GPS latitude of the search origin in decimal degrees, e.g. \"41.9028\"; send with lon; omitted uses source default. No option surcharge; 5 credits per successful request."
    • changedInput schema / properties / lon / description
      Previous value: -"GPS longitude for search origin; omitted uses source default. No option surcharge; 5 credits per successful request."New value: +"GPS longitude of the search origin in decimal degrees, e.g. \"12.4964\"; send with lat; omitted uses source default. No option surcharge; 5 credits per successful request."
    • changedInput schema / properties / mkt / description
      Previous value: -"Market such as en-US; omit for source default, mutually exclusive with cc. No option surcharge; 5 credits per successful request."New value: +"Market as language-COUNTRY, e.g. \"en-US\" or \"it-IT\"; omit for source default, mutually exclusive with cc. No option surcharge; 5 credits per successful request."
    • changedInput schema / properties / query / description
      Previous value: -"Required web search keywords; no default. No option surcharge; 5 credits per successful request."New value: +"Required web search keywords, e.g. \"what is an api\"; no default. No option surcharge; 5 credits per successful request."
    • changedInput schema / properties / safeSearch / description
      Previous value: -"Adult-content filter: Off, Moderate or Strict; omitted uses source default. No option surcharge; 5 credits per successful request."New value: +"Adult-content filter: Off, Moderate or Strict, e.g. \"Strict\"; omitted uses source default. No option surcharge; 5 credits per successful request."
    • addedInput schema / properties / safeSearch / enum
      Added value: +[
      +  "Off",
      +  "Moderate",
      +  "Strict"
      +]
    • removedInput schema / properties / safeSearch / minLength
      Removed value: -1
  2. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly=true, idempotent=true, destructive=false, openWorld=true, so the safety profile is covered. The description adds genuinely non-obvious billing semantics — empty-result searches are charged while errors are not — which an agent cannot infer from structured fields. Minor tension between "up to 20 ranked results" and the schema's count maximum of 50 slightly muddies the cap, preventing a 5.

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?

Three tight sentences: capability and return shape first, then routing guidance, then the cost caveat and required param. Nothing is repeated and no sentence is filler.

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 9-parameter tool with no output schema, the description usefully names the returned fields and the billing rule, which are the highest-risk unknowns. It does not explain how count and first interact for pagination, which is the main remaining gap.

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%, so the baseline is 3; every parameter including the mkt/cc mutual exclusivity and lat/lon pairing is documented in the schema. The description merely summarizes market, safe search and coordinate targeting without adding format or interaction detail beyond that.

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?

States a specific verb and resource ("Searches Bing web results") plus the returned shape (title, link, snippet, rank) and targeting options. It explicitly separates itself from scrape_url (no page contents) and google_search (no Google results), so an agent can route correctly without opening a schema.

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?

Gives both a positive trigger ("Use it when Bing results are wanted") and two explicit exclusions with the named alternative for each. This is the when/when-not/alternatives pattern in compact form.

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