Skip to main content
Glama

Exa Answer

exa_answer
Read-onlyIdempotent

Cited answer to a question: Exa searches the web and writes an answer with the sources it used. Returns the answer, a citations array (title, URL, published date) and the upstream cost. Example: exa_answer({ query: "What is the current federal funds target range?" })

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "What is the current federal funds target range?"
    },
    "name": "exa_answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoIf true, include the full page text on each citation. Default false.
modelNoAnswer model. Default 'exa'.
queryYesThe question or instruction to answer.
_apiKeyNoOptional, your own Exa API key for higher limits; omit to use the shared Pipeworx key.
output_schemaNoOptional JSON Schema (Draft 7); the answer is then a structured object matching it.
system_promptNoOptional extra instructions guiding the answer.

Output Schema

NameRequiredDescriptionDefault
answerYesThe answer: a string, or an object matching output_schema
citationsYesSources used for the answer
costDollarsNoUpstream cost breakdown in USD as reported by the vendor

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint and destructiveHint=false, so the safety profile is covered structurally. The description adds genuinely useful context beyond that — the return shape (answer, citations array with title/URL/published date, upstream cost) — but it says nothing about latency, rate limits, or what happens with the shared API key, so it stops short of a 4.

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?

Two compact sentences: purpose first, return contract second, then a concrete example call. Every element is front-loaded and there is no filler, though the example query is somewhat redundant with the schema's own examples array.

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?

Given an output schema exists and the schema documents all six parameters, the description still usefully summarizes the return payload (answer, citations, cost) and shows a call pattern. Nothing critical is missing for correct invocation; only cross-tool routing guidance is absent.

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% with six well-documented parameters including an enum and an _apiKey escape hatch, so the schema carries the parameter semantics. The description only echoes the query parameter via its example and names the citation fields, adding no new meaning about model choice, output_schema, or system_prompt behavior — baseline 3.

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 uses a specific verb+resource framing: 'Cited answer to a question' plus 'Exa searches the web and writes an answer with the sources it used.' That clearly separates it from a plain results-list search, but it never names exa_search or any sibling, so the differentiation is implicit rather than explicit.

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 only implied: an agent can infer this is the tool for when it wants a synthesized, sourced answer rather than raw links. There is no explicit 'use this when…' statement, no exclusion of alternatives like exa_search or deep_research, and no guidance on cost/limit tradeoffs that would drive selection.

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.