Skip to main content
Glama

AIsa Web Search & Research

by one.aisa
OverviewDiscussionsAdmin

Answer

post_exa_answer
Destructive

Ask a question and get a written answer with citations. query is required; text includes the source text and outputSchema shapes a structured reply. Returns requestId, answer as prose, citations[] with id, title and url, and costDollars. Measured at 2.1 seconds with 8 citations. Use current endpoint pricing and a fresh quote for this request. It sits between a search and a research run: faster and cheaper than post_exa_agent_runs, and more direct than reading post_exa_search results yourself. Reach for Exa when the retrieval needs to be semantic; compare current quotes when choosing a provider.

Usage-based billing; Default request estimate: $0.005 USD (not a fixed price). Account-specific pricing and final settlement may differ.

Input Schema

NameRequiredDescriptionDefault
bodyYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / body
      Added value: +{
+  "properties": {
+    "outputSchema": {
+      "description": "JSON Schema for a structured answer output.",
+      "type": "object"
+    },
+    "query": {
+      "description": "The question to answer.",
+      "example": "Which manufacturers had the top three global EV sales in 2025?",
+      "type": "string"
+    },
+    "stream": {
+      "default": false,
+      "enum": [
+        false
+      ],
+      "type": "boolean"
+    },
+    "text": {
+      "description": "Include the full page text of each citation.",
+      "type": "boolean"
+    },
+    "type": {
+      "description": "Retrieval mode used to gather sources before answering.",
+      "enum": [
+        "auto",
+        "fast",
+        "instant",
+        "deep-lite",
+        "deep",
+        "deep-reasoning"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "query"
+  ],
+  "type": "object"
+}
    • removedInput schema / properties / outputSchema
      Removed value: -{
-  "description": "JSON Schema for a structured answer output.",
-  "type": "object"
-}
    • removedInput schema / properties / query
      Removed value: -{
-  "description": "The question to answer.",
-  "example": "Which manufacturers had the top three global EV sales in 2025?",
-  "type": "string"
-}
    • removedInput schema / properties / stream
      Removed value: -{
-  "default": false,
-  "enum": [
-    false
-  ],
-  "type": "boolean"
-}
    • removedInput schema / properties / text
      Removed value: -{
-  "description": "Include the full page text of each citation.",
-  "type": "boolean"
-}
    • removedInput schema / properties / type
      Removed value: -{
-  "description": "Retrieval mode used to gather sources before answering.",
-  "enum": [
-    "auto",
-    "fast",
-    "instant",
-    "deep-lite",
-    "deep",
-    "deep-reasoning"
-  ],
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "query"
-]New value: +[
+  "body"
+]
  2. Changed1 schema field changed
    • addedInput schema / properties / stream
      Added value: +{
+  "default": false,
+  "enum": [
+    false
+  ],
+  "type": "boolean"
+}
  3. Changed1 schema field changed
    • removedInput schema / properties / stream
      Removed value: -{
-  "default": false,
-  "enum": [
-    false
-  ],
-  "type": "boolean"
-}
  4. Changed1 schema field changed
    • addedInput schema / properties / stream
      Added value: +{
+  "default": false,
+  "enum": [
+    false
+  ],
+  "type": "boolean"
+}
  5. First observed

TDQS

A3.8/5.0
Behavior3/5

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

It discloses return fields (requestId, answer, citations[], costDollars) and a latency figure, which the annotations do not cover. However, the annotations declare readOnlyHint=false and destructiveHint=true for what the description frames as a plain retrieval/answer operation, and the description never reconciles or even acknowledges that mutability/safety profile. The pricing sentence is hedged boilerplate ('not a fixed price'), so the added behavioral value is moderate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded well: purpose, key params, and return shape come first. But several sentences are promotional or boilerplate ('Measured at 2.1 seconds with 8 citations', 'Use current endpoint pricing and a fresh quote', 'compare current quotes when choosing a provider') and do not help an agent invoke the tool.

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?

An output schema exists, so the description is not obligated to enumerate return values, yet it still summarizes them concisely. The nested request body's enum and streaming options are the main uncovered area, and the mismatch between the destructive annotation and the read-style operation is left unaddressed.

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 reported at 0% for the top-level 'body' wrapper, so the description carries extra weight, and it does document query (required), text (includes source text) and outputSchema (shapes a structured reply). It says nothing about the important 'type' retrieval-mode enum (auto/fast/instant/deep-lite/deep/deep-reasoning) or the 'stream' flag, leaving the highest-variance parameter undocumented.

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 first sentence states a specific verb and resource: 'Ask a question and get a written answer with citations.' It also explicitly positions the tool against named siblings ('between a search and a research run'), so an agent can tell it apart from post_exa_search and post_exa_agent_runs without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear selection context with named alternatives: faster/cheaper than post_exa_agent_runs and more direct than reading post_exa_search results yourself. It also adds a domain cue ('when the retrieval needs to be semantic'). It stops short of explicit when-not conditions, and the closing 'compare current quotes' line is provider-shopping filler rather than usage guidance.

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

All AIsa Web Search & Research toolsInspect
Try in Browser
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources