Skip to main content
Glama

scout_quote

Read-onlyIdempotent

Price a request before running it; spends nothing and debits nothing. Returns total_flop (Scout service fee), and when q and model are given, also inference.floor and inference.typical (the FLOP gateway's own estimate of the miner cost for a minimal and a three-source call respectively). Scout's fee and the miner's cost are always two separate line items. Call this before scout_answer to decide whether to proceed.

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": "scout_quote"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoThe question, to size the inference estimate.
modelNoe.g. flop:qwen/qwen2.5-0.5b-instruct
sourcesNoSource ids from scout_catalog. Use ["auto"] to let Scout pick free sources only.
max_tokensNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

The annotations already flag readOnlyHint and idempotentHint, so the description's main added value is billing semantics: no spend, no debit, and that Scout's fee and miner cost are always separate line items. It also discloses conditional return fields (inference.floor/typical only when q and model are supplied), which is behavior no annotation conveys. It stops short of describing units, magnitude, or latency of the pricing call.

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 essential claim (pricing, free) and ends with the actionable decision instruction. Three sentences carry a lot, though the parenthetical explanation of floor/typical is dense and could be tightened.

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 no output schema, the description usefully names the return fields and their cost split, which is what an agent needs to act on the result. Minor incompleteness remains around max_tokens effects and partial-parameter behavior for a 4-parameter tool.

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?

Adds conditional meaning beyond the 75%-covered schema: q and model jointly gate the inference estimate, while total_flop is always returned. It does not explain max_tokens at all, nor what happens if only one of q/model is supplied, which are the remaining semantic holes.

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 ("Price a request"), and immediately disambiguates from the sibling scout_answer, which actually runs the request. The agent knows without opening any schema that this is a costing, not an execution, operation.

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?

Explicit sequencing guidance: "Call this before scout_answer to decide whether to proceed," plus the guarantee that it "spends nothing and debits nothing" removes any cost of trial. The only gap is an explicit when-not case, but the decision context is unambiguous.

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.