Skip to main content
Glama

model_advisor

Read-onlyIdempotent

LLM selection + cost advisor. POST a task description (+ optional volume/tokens/constraints like local-only or cheap) and get a recommended model + fallback chain + do-not-use (with reasons), the complexity tier, and per-run + monthly cost. A maintained model+price catalog. Deterministic, no LLM. Tells the AI/user which model to use and what it costs.

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": {
      "task": "<task>"
    },
    "name": "model_advisor"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesThe task the model is for, in plain language; sets the capability tier.
top_nNoHow many ranked models to return as primary+fallbacks (rest land in also_considered). Default 1 = primary alone.
modelsNoOptional allowlist - restrict ranking to only these model identifiers (e.g. models you already have access to). Any catalog model not in this list is excluded, listed in do_not_use.
tokens_inNoInput tokens per call. Default 1500.
tokens_outNoOutput tokens per call. Default 800.
constraintsNolocal-only: self-hostable models only; low-latency: prefer lower-priced fast models; cheap: drop one capability tier.
volume_per_monthNoCalls per month, for the cost estimate. Default 300.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed16 schema fields changed
    • addedInput schema / properties / constraints / description
      Added value: +"local-only: self-hostable models only; low-latency: prefer lower-priced fast models; cheap: drop one capability tier."
    • addedInput schema / properties / constraints / items / enum
      Added value: +[
      +  "local-only",
      +  "low-latency",
      +  "cheap"
      +]
    • addedInput schema / properties / task / description
      Added value: +"The task the model is for, in plain language; sets the capability tier."
    • addedInput schema / properties / task / maxLength
      Added value: +10000
    • addedInput schema / properties / tokens_in / description
      Added value: +"Input tokens per call. Default 1500."
    • addedInput schema / properties / tokens_in / maximum
      Added value: +10000000
    • addedInput schema / properties / tokens_in / minimum
      Added value: +1
    • changedInput schema / properties / tokens_in / type
      Previous value: -"number"New value: +"integer"
    • addedInput schema / properties / tokens_out / description
      Added value: +"Output tokens per call. Default 800."
    • addedInput schema / properties / tokens_out / maximum
      Added value: +10000000
    • addedInput schema / properties / tokens_out / minimum
      Added value: +1
    • changedInput schema / properties / tokens_out / type
      Previous value: -"number"New value: +"integer"
    • addedInput schema / properties / volume_per_month / description
      Added value: +"Calls per month, for the cost estimate. Default 300."
    • addedInput schema / properties / volume_per_month / maximum
      Added value: +1000000000
    • addedInput schema / properties / volume_per_month / minimum
      Added value: +1
    • changedInput schema / properties / volume_per_month / type
      Previous value: -"number"New value: +"integer"
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-redundant traits: 'Deterministic, no LLM' tells the agent the output is reproducible and incurs no model spend, and 'A maintained model+price catalog' signals prices are curated data rather than a live quote. It stops short of saying how often the catalog is refreshed or whether prices can be stale, which is the one caveat an agent budgeting on this output would want.

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?

It is front-loaded with the core purpose and the return contents, and most of the text earns its place. The closing sentence 'Tells the AI/user which model to use and what it costs' largely repeats the opening, and the fragment stack ('A maintained model+price catalog. Deterministic, no LLM.') reads as bullet points compressed into prose.

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?

There is no output schema, and the description compensates by enumerating every returned element including the do-not-use list with reasons and the cost breakdown. For a read-only 7-parameter advisor with full schema coverage, an agent has everything needed to invoke it and interpret the result; only price currency/refresh cadence is left unstated.

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 explains task, top_n, models, token counts, constraints, and volume. The description restates '+ optional volume/tokens/constraints like local-only or cheap' without adding format, defaults, or interaction semantics beyond what the properties document. Baseline 3 is appropriate since the schema carries the parameter burden.

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 opening states a specific verb+resource ("LLM selection + cost advisor") and the body spells out the exact output set: recommended model, fallback chain, do-not-use with reasons, complexity tier, and per-run/monthly cost. An agent can distinguish this from the similarly named sibling tool_advisor because the resource is explicitly models and prices, not tool definitions.

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: 'Tells the AI/user which model to use and what it costs' suggests calling it when a model choice or budget estimate is needed, and the call shape ('POST a task description') hints at inputs. There is no explicit when-not-to-use, no mention of tool_advisor as the adjacent-but-different sibling, and no prerequisite conditions.

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.