WET - Web Extended Toolkit

Overview Schema Source Related Servers Discussions Admin

search

Read-onlyIdempotent

Find information across the web, academic sources, and library docs, returning result listings with titles, URLs, and snippets. Use extract to read full page content.

Instructions

Find information across web, academic sources, or library docs. Returns search result listings (titles, URLs, snippets) -- NOT full page content. To read full content from a URL, use the extract tool instead.

Actions:

search: Web search via SearXNG. Example: search(action="search", query="python async patterns")
research: Academic/scientific search (Google Scholar, arXiv, PubMed). Example: search(action="research", query="transformer attention mechanism")
docs: Search library documentation with auto-indexing. Example: search(action="docs", query="how to create routes", library="fastapi")
docs_resolve: Free-form library name to ranked library_id list. Example: search(action="docs_resolve", query="react")
docs_query: Version-aware library docs query honoring project lock + token cap. Example: search(action="docs_query", library="react", version="latest", topic="useState", query="how to set initial state")
docs_lock_project: Detect project manifests (pyproject/package.json/go.mod/Cargo.toml) and lock the library set for Cabinets isolation. Example: search(action="docs_lock_project", project_path="/repo/my-app")
similar: Find pages similar to a URL (pass URL as query). Example: search(action="similar", query="https://example.com/article")

Key parameters:

query (required for all actions): Search terms or URL (for similar)
library (required for docs): Library name, e.g. "react", "fastapi"
language: Programming language for disambiguation in docs, e.g. "python", "java"
expand: Enable LLM query expansion for broader coverage (default: false)
enrich: Fetch actual page content for richer snippets (default: false, adds latency)
max_results: Number of results (default: 10)
time_range: Recency filter -- day, week, month, year
include_domains / exclude_domains: Domain filters
region (search only): 2-letter ISO 3166-1 country code (e.g. "US", "vn") geo filter. Backends without region support are skipped (named in a warning); a chain with no region-capable backend returns a structured error naming them.
refine (search only): Opt-in iterative refinement. When results are empty or low-relevance, re-queries up to 2 times with LLM-rewritten terms and returns the best round (adds LLM latency/cost per round).

Use help tool with tool_name="search" for full parameter documentation.

Input Schema

TableJSON Schema

Name	Required	Default
`limit`	No
`query`	No
`topic`	No
`action`	Yes
`enrich`	No
`expand`	No
`refine`	No
`region`	No
`library`	No
`version`	No
`language`	No
`parallel`	No
`categories`	No	general
`time_range`	No
`max_results`	No
`project_path`	No
`exclude_domains`	No
`include_domains`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv3.11.1Sep 12, 2026

removedInput schema / properties / exclude_handles

Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Exclude Handles"
-}

removedInput schema / properties / from_date

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "From Date"
-}

removedInput schema / properties / handles

Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Handles"
-}

removedInput schema / properties / to_date

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "To Date"
-}

removedInput schema / properties / video

Removed value: -{
-  "default": false,
-  "title": "Video",
-  "type": "boolean"
-}

Changed3 schema fields changedv3.10.0Sep 2, 2026

addedInput schema / properties / parallel

Added value: +{
+  "default": false,
+  "title": "Parallel",
+  "type": "boolean"
+}

addedInput schema / properties / refine

Added value: +{
+  "default": false,
+  "title": "Refine",
+  "type": "boolean"
+}

addedInput schema / properties / region

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Region"
+}

Addedv3.7.3Aug 19, 2026
Removedv3.6.0Jul 18, 2026

Changed9 schema fields changedv3.5.0Jul 14, 2026

addedInput schema / properties / exclude_handles

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Exclude Handles"
+}

addedInput schema / properties / from_date

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "From Date"
+}

addedInput schema / properties / handles

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Handles"
+}

addedInput schema / properties / to_date

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "To Date"
+}

addedInput schema / properties / video

Added value: +{
+  "default": false,
+  "title": "Video",
+  "type": "boolean"
+}

addedOutput schema / additionalProperties
```
Added value: +true
```

removedOutput schema / properties

Removed value: -{
-  "result": {
-    "title": "Result",
-    "type": "string"
-  }
-}

removedOutput schema / required
```
Removed value: -[
-  "result"
-]
```

changedOutput schema / title

Previous value: -"searchOutput"New value: +"searchDictOutput"

Changed7 schema fields changedv3.1.0May 19, 2026

addedInput schema / properties / enrich

Added value: +{
+  "default": false,
+  "title": "Enrich",
+  "type": "boolean"
+}

addedInput schema / properties / exclude_domains

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Exclude Domains"
+}

addedInput schema / properties / expand

Added value: +{
+  "default": false,
+  "title": "Expand",
+  "type": "boolean"
+}

addedInput schema / properties / include_domains

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Include Domains"
+}

addedInput schema / properties / project_path

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Project Path"
+}

addedInput schema / properties / time_range

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Time Range"
+}

addedInput schema / properties / topic

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Topic"
+}

First observedv2.13.0Mar 12, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only declare readOnly/idempotent/openWorld; the description adds real behavioral context beyond that: enrich 'adds latency', refine 'adds LLM latency/cost per round' and re-queries up to 2 times, region-unsupported backends are skipped with a warning and a fully unsupported chain returns a structured error, and docs_lock_project performs manifest detection and cabinet locking. These are concrete operational traits not derivable from the annotations.

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 purpose and the key non-return-content caveat before enumerating actions, and the action list is scannable with inline examples. It is long, but for an 18-parameter dispatcher most sentences carry information; the pointer to the `help` tool is a reasonable way to bound the length.

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 return values need not be explained, and the description still usefully summarizes the response shape. Edge-case behavior (empty results + refine, region fallback errors, lock semantics) is covered. Minor gaps remain around undocumented parameters and the limit/max_results duplication.

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?

Schema description coverage is 0%, so the description must carry the burden, and it does for most parameters: query, library, language, expand, enrich, max_results, time_range, include/exclude_domains, region, refine all get meaning, defaults, or constraints. It leaves several properties unexplained (limit, topic, version, parallel, categories) and does not clarify the overlap between `limit` and `max_results`, so it falls short of full compensation.

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 (find/search) plus the resource scopes (web, academic, library docs) and explicitly delimits the return type: 'search result listings (titles, URLs, snippets) -- NOT full page content.' It also names the sibling `extract` as the tool for the excluded case, so an agent can distinguish these two without opening schemas.

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?

The action list gives per-action examples and the opening sentence routes the read-full-content case to `extract`, which is a genuine alternative-selection rule. What's missing is explicit guidance on when NOT to use a given action (e.g. docs vs docs_query vs docs_resolve selection criteria), leaving some inference to the agent.

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

Deploy Server