Skip to main content
Glama

Marketingburos

Match a brief to marketing agencies

match_brief
Read-onlyIdempotent

Match a buyer's own question to Dutch marketing agencies. Infers the specialisms from the brief; search_agencies takes specialisms the buyer already knows. Input: the brief in the buyer's words (NL or EN, 20-2000 chars), optionally with the same hard filters as search_agencies (city, near_city + within_km, target_industry, client_orientation, company_size_band, budget_band, agency_size). The brief is redacted for personal data first and never stored; a call takes a few seconds. Ranking fuses the match score, how close the agency's profile is to the brief, and public case evidence in the sectors the brief names. Returns up to 20 ranked agencies (slug, name, 1-line Dutch rationale citing the agency's evidence, team_size, client_sectors, top_case, via: specialism | brief | both) and interpreted: the specialisms and working style read from the brief, plus a follow-up question when the brief is unclear. interpreted shows the buyer how the brief was read; search_agencies accepts explicit specialisms. Ranking ignores what an agency pays (never pay-to-rank).

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": {
      "brief": "<brief>"
    },
    "name": "match_brief"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoExact office city of the agency. For 'near a city' use near_city + within_km instead.
briefYesThe buyer's own words (NL or EN, 20-2000 chars). The question itself, not a summary.
limitNoMax results (1-20, default 10).
near_latNoCenter latitude of a radius search (alternative to near_city). Requires near_lon + within_km.
near_lonNoCenter longitude of a radius search (alternative to near_city). Requires near_lat + within_km.
near_cityNoCenter of a radius search: any Dutch city name. Requires within_km.
within_kmNoRadius in kilometres around near_city or near_lat/near_lon (max 250). Ignored without an origin; near_* is ignored without within_km.
agency_sizeNoSize of the AGENCY itself (KvK registered employees): 1-9, 10-49, 50-249, 250+ or geen-voorkeur. Agencies without a known KvK count stay in (filters.agency_size.unknown).
budget_bandNoBuyer's budget in EUR. Only excludes agencies whose known rates conflict; most agencies have no known rate.
target_industryNoClient vertical the agency serves (e.g. the buyer's own industry). Not the agency's own sector.
company_size_bandNoSize of the buyer's company (employees); matches agencies that target that segment.
client_orientationNob2b or b2c focus of the agency.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / agency_size
      Added value: +{
      +  "description": "Size of the AGENCY itself (KvK registered employees): 1-9, 10-49, 50-249, 250+ or geen-voorkeur. Agencies without a known KvK count stay in (filters.agency_size.unknown).",
      +  "enum": [
      +    "1-9",
      +    "10-49",
      +    "50-249",
      +    "250+",
      +    "geen-voorkeur"
      +  ],
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / brief / description
      Previous value: -"The buyer's own words (NL or EN, 20-2000 chars). Pass the question, not a summary."New value: +"The buyer's own words (NL or EN, 20-2000 chars). The question itself, not a summary."
  3. Changed1 schema field changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  4. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent and non-destructive, yet the description adds substantive behavior: the brief is redacted for personal data and never stored, a call takes a few seconds, and ranking fuses match score, profile proximity and public case evidence with no pay-to-rank. The only minor gap is that the redaction/privacy claim isn't qualified in any way (e.g., what counts as personal data), but the operational context is strong.

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?

Front-loads the core distinction and input requirements before the ranking and return details. It is dense (one long sentence covers filters) but every clause carries information; the repetition of 'interpreted' explanation across two sentences is the only minor redundancy.

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 no output schema, the description carries the return format itself: up to 20 ranked agencies with slug, name, Dutch rationale, team_size, client_sectors, top_case and a `via` provenance field, plus the `interpreted` object and its follow-up question. For a 12-parameter ranked-search tool, an agent has everything needed to call and interpret it.

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 coverage is 100%, so the schema already documents all 12 parameters, but the description adds meaning by clarifying the brief is 'the question itself, not a summary' in NL or EN (20-2000 chars) and by enumerating the filter families (city, near_city + within_km, target_industry, client_orientation, company_size_band, budget_band, agency_size). This helps the agent understand the filter set at a glance rather than reading 12 schema entries.

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 resource ('Match a buyer's own question to Dutch marketing agencies') and immediately contrasts it with search_agencies by input type. An agent can distinguish this from siblings 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?

Explicitly states when to use this versus search_agencies: use match_brief when the buyer has only a free-text question, and search_agencies when the buyer already knows the specialisms. It also notes the optional hard filters mirror search_agencies, closing the loop on the alternative.

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