Skip to main content
Glama

Matchmake 64-Bit Agent Shortlist or 3-Agent Crew

matchmake_agent_crew
Read-onlyIdempotent

Rank live heartbeat-verified MCP and A2A endpoints using 64-bit MGLE-NNP bitwise capability masks and return either a provider-diverse shortlist or a 3-agent complementary crew (Compute + Domain + Verifier) with single-use execution tickets. Use when selecting callable agents for a task; use search_agent_directory for raw keyword browsing or get_agent_dossier when you already have an agent_id.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "matchmake_agent_crew"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoRouting policy: 'top10_varied' for ranked shortlist across distinct vendors, or 'crew' for a 3-role complementary triad.
top_kNoMaximum number of ranked candidates to return (1..25, default 10).
intentNoNatural-language task intent used to infer required 64-bit capability switches when capabilities is omitted.
capabilitiesNoOptional explicit MGLE-NNP capability switch names (e.g. sql, database, finance_data, file_parse, math_verify, code_exec, web_fetch, search_rag).
caller_regionNoCaller geographic zone for round-trip latency affinity ('E' US-East, 'W' US-West, 'U' Europe, 'P' APAC, 'GLOBAL' any).
max_latency_gradeNoWorst acceptable Virginia Scout RTT grade ('A' <=120ms, 'B' <=300ms, 'C' <=700ms default, 'D' <=1500ms, 'ANY' unrestricted live RTT).
require_instant_zero_authNoTrue (default: true) restricts results strictly to open zero-credential endpoints with verified non-zero tools/list schemas callable immediately without API keys or OAuth.

Output Schema

NameRequiredDescriptionDefault
modeYesApplied routing policy identifier.
finalistsYesRanked candidate agent records including endpoint URL, 64-bit hex ID, and execution_ticket.
finalist_countYesNumber of matched endpoints returned.
scanned_pool_countNoTotal audited phonebook records scanned.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / max_latency_grade / description
      Previous value: -"Worst acceptable Virginia Scout RTT grade ('A' <=150ms, 'B' <=350ms, 'C' <=700ms, 'D' offline repo, 'E' any)."New value: +"Worst acceptable Virginia Scout RTT grade ('A' <=120ms, 'B' <=300ms, 'C' <=700ms default, 'D' <=1500ms, 'ANY' unrestricted live RTT)."
    • changedInput schema / properties / max_latency_grade / enum
      Previous value: -[
      -  "A",
      -  "B",
      -  "C",
      -  "D",
      -  "E"
      -]New value: +[
      +  "A",
      +  "B",
      +  "C",
      +  "D",
      +  "ANY"
      +]
    • changedInput schema / properties / require_instant_zero_auth / description
      Previous value: -"True restricts results strictly to open zero-credential endpoints callable immediately without API keys or OAuth."New value: +"True (default: true) restricts results strictly to open zero-credential endpoints with verified non-zero tools/list schemas callable immediately without API keys or OAuth."
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, yet the description still adds real context: results are heartbeat-verified liveness-checked endpoints, optionally restricted to zero-credential callable ones, and each result carries single-use execution tickets. The only notable omission is ticket lifetime/expiry semantics, which matters given the 'single-use' claim; this is not a contradiction with the read-only hint, since ranking itself remains a read.

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?

Two sentences, front-loaded with the action and output shape, followed immediately by routing guidance — no filler. It is dense with domain jargon (MGLE-NNP, bitwise masks) that inflates reading cost without adding call guidance, but nothing is wasted.

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?

With an output schema present, the description need not explain return values, and it correctly focuses on selection behavior, latency/auth filtering, and ticket issuance. The missing piece for a tool of this complexity is any note on ticket validity windows or what 'complementary crew' guarantees in practice, but nothing an agent needs to invoke it correctly is absent.

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% with three enums fully documented, so the schema carries most of the parameter burden. The description only adds framing for mode ('provider-diverse shortlist' vs '3-agent complementary crew (Compute + Domain + Verifier)') and the fact that capabilities are drawn from bits 0..23, which is marginal beyond what the schema already states.

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 gives a specific verb ('Rank'), a specific resource ('live heartbeat-verified MCP and A2A endpoints'), the ranking mechanism (64-bit MGLE-NNP bitwise capability masks), and both output shapes (provider-diverse shortlist or 3-agent crew). It also explicitly names two sibling tools it is not, so an agent can distinguish it without opening any 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?

It states the selecting condition ('Use when selecting callable agents for a task') and routes the agent to explicit alternatives: search_agent_directory for raw keyword browsing and get_agent_dossier when an agent_id is already known. The when-to-use / when-not / alternative structure is fully present.

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.