Skip to main content
Glama

Answer a question (billed)

answer

Get a short, source-cited answer to a closed question, with markers pointing to the pages it used. Requires a configured backend API key, else calls fail.

Instructions

Answer one closed question in a sentence or two: the backend searches and writes the answer, with the sources it cites, each by its marker (e.g. '[2]'). A few seconds. Unset, provider tries the configured backends in ranked order, and each one tried bills. Unedited: check it against the sources when it matters. search returns the pages themselves. NOTHING IS CONFIGURED FOR THIS METHOD on this machine, so every call will fail. A key in one of BRAVE_ANSWER_API_KEY, EXA_API_KEY, LINKUP_API_KEY, PARALLEL_API_KEY, PERPLEXITY_API_KEY, YOU_API_KEY turns it on: see load_env.

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": {
      "query": "<query>"
    },
    "name": "answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesThe question to answer.
snippetsNoInclude each source's quoted passage.
all_sourcesNoAlso list the sources the answer read but did not cite.

Output Schema

NameRequiredDescriptionDefault
noteNo
answerNo
handleYes
providerNo
citationsNo
truncatedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false; the description adds what they cannot: per-backend billing ('each one tried bills'), latency ('a few seconds'), the unedited/verify-against-sources caveat, and the fact the method is currently unconfigured. That is substantial context beyond the structured fields and is consistent with a cost-incurring open-world 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?

Purpose is front-loaded, followed by cost, latency, correctness caveat, alternative, and configuration state in a logical order, with no filler sentences. The `provider`/ranked-backend sentence is the one passage that costs clarity, since it references a parameter the schema does not expose.

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?

An output schema exists, so return values need not be explained; the description instead covers everything an agent needs before invoking: what it produces, cost, speed, reliability caveat, sibling alternative, and the blocking configuration prerequisite with the exact env vars to enable it. The only inaccuracy is the phantom `provider` reference, which is minor relative to the overall coverage.

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 baseline is 3; the description adds a real constraint on `query` (must be a closed question), which is genuine value. However, it discusses an `provider` parameter ('Unset, `provider` tries the configured backends in ranked order') that does not exist in the input schema, which sets `additionalProperties: false` — an agent following the description could attempt an invalid argument. That defect caps the score at baseline rather than above it.

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 ('Answer one closed question in a sentence or two') and distinguishes itself from the sibling `search`, which 'returns the pages themselves'. The agent knows exactly what it gets back — a short synthesized answer with inline citation markers — without opening the 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?

Explicitly routes between alternatives: use this for a synthesized answer, use `search` when you want the raw pages, and use `load_env` when no key is configured. It also discloses the current prerequisite state ('NOTHING IS CONFIGURED FOR THIS METHOD on this machine, so every call will fail'), which is exactly the kind of when-not guidance an agent needs before wasting a call.

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