AgentIndex x402

Web Search

search

Read-onlyIdempotent

Jev-routed web search: each query goes to the best specialised source (code, facts, news, prices), results ranked by relevance. 28/30 test queries answered. Up to 10 results per query, each with title, URL, snippet, short extract and publish date. Up to 5 queries per call, merged and de-duplicated. No account, no API key. Try GET /search/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Input Schema

TableJSON Schema

Name	Required	Description
`query`	Yes	Search query, or an array of up to 5 related queries to run in one call - results are merged and de-duplicated by URL.
`extract`	No	Include the search-engine snippet for each result.
`summarize`	No	Also return a short synthesized answer summarizing the results.
`max_results`	No	Maximum number of results to return.
`content_chars`	No	Maximum Markdown characters returned per fetched result page.
`content_results`	No	How many top result pages to fetch when include_content is true.
`include_content`	No	Fetch result pages and include clean full-page Markdown. Defaults to true.

Output Schema

TableJSON Schema

Name	Required	Description
`query`	Yes	The query or queries that were searched.
`results`	Yes	Ranked web results, most relevant first.
`summary`	No	Optional short synthesized answer summarizing the results, when requested.
`x402_receipt`	No	Billing and provenance receipt for this call.

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedSep 27, 2026

addedInput schema / properties / content_chars / description

Added value: +"Maximum Markdown characters returned per fetched result page."

addedInput schema / properties / content_results / description

Added value: +"How many top result pages to fetch when include_content is true."

addedInput schema / properties / extract / description

Added value: +"Include the search-engine snippet for each result."

addedInput schema / properties / include_content / description

Added value: +"Fetch result pages and include clean full-page Markdown. Defaults to true."

addedInput schema / properties / max_results / description
```
Added value: +"Maximum number of results to return."
```

addedInput schema / properties / query / description

Added value: +"Search query, or an array of up to 5 related queries to run in one call - results are merged and de-duplicated by URL."

addedInput schema / properties / summarize / description

Added value: +"Also return a short synthesized answer summarizing the results."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "query": {
+      "description": "The query or queries that were searched."
+    },
+    "results": {
+      "description": "Ranked web results, most relevant first.",
+      "items": {
+        "properties": {
+          "content_error": {
+            "description": "Per-result fetch error; other search results remain usable.",
+            "type": "string"
+          },
+          "content_markdown": {
+            "description": "Clean full-page Markdown for fetched top results, with navigation and boilerplate removed.",
+            "type": "string"
+          },
+          "content_truncated": {
+            "description": "True when content_markdown reached the requested character limit.",
+            "type": "boolean"
+          },
+          "date": {
+            "description": "Publish date, when known."
+          },
+          "extract": {
+            "description": "Search-engine result snippet.",
+            "type": "string"
+          },
+          "title": {
+            "description": "Page title.",
+            "type": "string"
+          },
+          "url": {
+            "description": "Source URL.",
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "summary": {
+      "description": "Optional short synthesized answer summarizing the results, when requested."
+    },
+    "x402_receipt": {
+      "description": "Billing and provenance receipt for this call.",
+      "type": "object"
+    }
+  },
+  "required": [
+    "query",
+    "results"
+  ],
+  "type": "object"
+}

Changed3 schema fields changedSep 19, 2026

addedInput schema / properties / content_chars

Added value: +{
+  "default": 12000,
+  "type": "integer"
+}

addedInput schema / properties / content_results

Added value: +{
+  "default": 3,
+  "type": "integer"
+}

addedInput schema / properties / include_content

Added value: +{
+  "default": true,
+  "type": "boolean"
+}

AddedSep 19, 2026
RemovedSep 7, 2026
First observedSep 5, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare read-only, open-world, and idempotent, so safety is covered. The description adds genuinely useful behavior: no account or API key needed, up to 10 results per query, up to 5 queries merged and de-duplicated per call, and the per-result fields returned.

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-loaded with the core routing concept and tight facts (limits, result fields, no auth). The '28/30 test queries answered' statistic is pure marketing filler, and the kit/sample links are marginally useful but slightly diluting.

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 an output schema present, the description need not explain return values, yet it still summarizes them usefully. For a 7-param search tool with full annotations, nothing critical is missing, though sibling routing guidance would strengthen selection.

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 coverage is 100%, so every parameter is already documented, making 3 the baseline. The description adds the merge/de-duplication behavior for array queries, but it also introduces a mild inconsistency by saying 'up to 10 results per query' while the schema default for max_results is 5.

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?

States a specific verb and resource (web search) and adds distinguishing scope: Jev-routed dispatch to specialised sources for code, facts, news, and prices, with relevance ranking. It never names a sibling to prefer or avoid, so an agent must infer how it differs from news, fact_check, or research.

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?

The routing sentence implies coverage (code/facts/news/prices) and 'Try GET /search/sample' offers a probe path, but there is no explicit when-to-use-this-instead-of-sibling guidance. The 28/30 benchmark line is a quality claim, not a selection rule.

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

All AgentIndex x402 tools Inspect

Try in Browser

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.