Skip to main content
Glama

Locate a model

locate_model

Resolve where a model's inference physically runs from a model ID, fleet lane, or base URL. Returns a four-plane location card, serving chain, evidence rows, confidence state, and contradictions.

Instructions

Resolve where a model's inference physically runs. Accepts a model id, a fleet lane/CLI name, or an explicit base_url. Returns a four-plane location card (control/edge/origin/legal), the serving chain, evidence rows with sources, a confidence state, contradictions, and the next probe that would tighten the answer. Re-derives everything from live DNS, ASN, cloud prefix tables and PeeringDB, so it tracks provider changes without redeploying.

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": "locate_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
laneNoFleet lane or CLI name, e.g. "dsh", "codex", "grok".
modelNoModel id, e.g. "deepseek-flash-4.1-107" or "gpt-6.1 sol".
base_urlNoThe base URL the CLI is actually configured to call. Overrides the catalog default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does substantial work: it discloses the return structure (four-plane location card, serving chain, evidence rows with sources, confidence state, contradictions, next probe) and states that results are re-derived from live DNS, ASN, cloud prefix tables and PeeringDB, which tells the agent the data is fresh rather than cached. It stops short of cost/latency, rate limits, auth requirements, or whether results are cached between calls.

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?

Three sentences, front-loaded with the purpose and then the return contract and the freshness guarantee. The middle sentence is a long enumeration but every item is informative 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?

There is no output schema, and the description compensates by describing the returned artifact in detail, which is exactly what is needed here. The main residual gap is that zero required parameters leaves open what happens on an argument-less call and how ambiguity between lane/model/base_url is resolved, which an agent would need in order to call it correctly.

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 schema already documents lane, model, and base_url with examples and the override rule for base_url. The description reinforces the three accepted resolution modes but adds no precedence rules or behavior for partial/ambiguous identifiers beyond what the schema states. Baseline 3 applies when the schema does the heavy lifting.

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 opens with a specific verb and resource: 'Resolve where a model's inference physically runs.' It then enumerates the accepted identifier forms (model id, lane/CLI name, base_url), which clarifies the resolution semantics beyond a generic lookup and differentiates it from siblings like lookup_prefix or trace_endpoint that operate on network primitives rather than a model-to-location mapping.

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?

Usage is implied rather than stated: you infer 'use this when you need to know where a model is served.' It gives no when-not guidance, no mention of when to prefer find_regional_endpoints, observe_endpoints, or trace_endpoint, and no prerequisites. The only forward-looking hint is the mention of 'the next probe that would tighten the answer,' which nudges toward follow-up tools without naming them.

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