Skip to main content
Glama

scout_answer

Read-only

Search the chosen sources, synthesise a cited answer, and return an itemised price. The response contains answer (text), citations (list of {url, title, snippet}), charged_flop (Scout fee charged), and inference_estimate (miner cost). FLOP models require a gateway key in keys.flop; OpenRouter models use keys.openrouter. On devnet keys can be omitted — charges are nominal and nothing is debited.

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": {
      "q": "<q>"
    },
    "name": "scout_answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
nNoresults per source
qYes
keysNoProvider keys keyed by name (flop, openrouter, exa …). Never stored or logged.
modelNo
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. Changed1 schema field changed
    • changedInput schema / properties / keys / description
      Previous value: -"Your own provider keys (flop, openrouter, exa, ...). Never stored or logged."New value: +"Provider keys keyed by name (flop, openrouter, exa …). Never stored or logged."
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

With readOnlyHint=true and openWorldHint=true already declared, the description adds real value by disclosing that a fee is charged (charged_flop), that a gateway key is required per provider family, and that devnet charges are nominal and nothing is debited. That last point is important context an agent would otherwise get wrong. It stops short of disclosing failure modes, latency, or whether charges occur on partial failures, so it is solid but not exhaustive.

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?

The action is front-loaded in the first clause and the remaining sentences carry distinct payloads: return fields (needed absent an output schema), auth requirements, and devnet caveat. Dense but nearly every sentence earns its place; the field enumeration is the only slightly list-like stretch, justified by the missing output schema.

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?

For a 6-parameter, nested-object, no-output-schema tool, the description covers the important unknowns: return shape, billing behavior, per-provider key requirements, and environment-dependent charging. It does not address error/partial-failure behaviour or what n and max_tokens bound in practice, leaving a few gaps but nothing that would cause a mis-call.

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?

At 50% schema coverage the description compensates well for the undocumented half: it explains that keys is keyed by provider name with specific keys.flop and keys.openrouter examples, that sources are ids from scout_catalog with an 'auto' free-only mode, and that model selection determines which key is needed. It adds nothing for q, n, or max_tokens, but those are self-evident by name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific compound action — search chosen sources, synthesise a cited answer, and return an itemised price — plus the exact return shape. It distinguishes this from a mere pricing call by making clear an answer is actually produced, but it never names scout_quote or scout_catalog, so sibling routing relies on the agent's own inference from 'chosen sources' pointing at scout_catalog.

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: the model/key requirements tell the agent this is the execution path, and 'sources: Source ids from scout_catalog' routes setup to a sibling. However there is no explicit when-to-use-this-instead-of-scout_quote guidance, so an agent comparing the two must reason about the price-vs-answer distinction on its own.

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.