Skip to main content
Glama
Sign In
robbyczgw-cla

web-search-plus-mcp

by robbyczgw-cla
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

web_extract

Extract source-only page text from URLs via multiple web search providers and return bounded content, truncation warnings, and stored-content references.

Instructions

Source-only URL extraction through 9 Web Search Plus v3 providers. Returns bounded page text, truncation warnings and stored-content references. Compact by default; detail='full' includes the complete v3 contract.

Input Schema

NameRequiredDescriptionDefault
urlsYesURLs to extract
spansNoSelect deterministic semantic spans from extracted text.
detailNoResponse detail: compact by default; full returns the complete v3 contract. Overrides the server default.
formatNomarkdown
providerNoauto
render_jsNo
spans_queryNoOptional query used to rank semantic spans.
include_imagesNo
include_raw_htmlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv5.1.6
    • addedInput schema / properties / detail
      Added value: +{
+  "description": "Response detail: compact by default; full returns the complete v3 contract. Overrides the server default.",
+  "enum": [
+    "compact",
+    "full"
+  ],
+  "type": "string"
+}
  2. Changed1 schema field changedv4.0.2
    • changedInput schema / properties / provider / enum
      Previous value: -[
-  "auto",
-  "tavily",
-  "exa",
-  "linkup",
-  "parallel",
-  "firecrawl",
-  "you",
-  "keenable",
-  "serper",
-  "hound"
-]New value: +[
+  "auto",
+  "tavily",
+  "exa",
+  "linkup",
+  "parallel",
+  "firecrawl",
+  "you",
+  "keenable",
+  "serper",
+  "donsetch"
+]
  3. Changed3 schema fields changedv3.3.1
    • changedInput schema / properties / provider / enum
      Previous value: -[
-  "auto",
-  "tavily",
-  "exa",
-  "linkup",
-  "parallel",
-  "firecrawl",
-  "you",
-  "keenable",
-  "serper"
-]New value: +[
+  "auto",
+  "tavily",
+  "exa",
+  "linkup",
+  "parallel",
+  "firecrawl",
+  "you",
+  "keenable",
+  "serper",
+  "hound"
+]
    • addedInput schema / properties / spans
      Added value: +{
+  "default": false,
+  "description": "Select deterministic semantic spans from extracted text.",
+  "type": "boolean"
+}
    • addedInput schema / properties / spans_query
      Added value: +{
+  "description": "Optional query used to rank semantic spans.",
+  "type": "string"
+}
  4. Changed1 schema field changedv0.16.0
    • changedInput schema / properties / provider / enum
      Previous value: -[
-  "auto",
-  "tavily",
-  "exa",
-  "linkup",
-  "parallel",
-  "firecrawl",
-  "you",
-  "keenable"
-]New value: +[
+  "auto",
+  "tavily",
+  "exa",
+  "linkup",
+  "parallel",
+  "firecrawl",
+  "you",
+  "keenable",
+  "serper"
+]
  5. Changed1 schema field changedv0.13.0
    • changedInput schema / properties / provider / enum
      Previous value: -[
-  "auto",
-  "tavily",
-  "exa",
-  "linkup",
-  "parallel",
-  "firecrawl",
-  "you"
-]New value: +[
+  "auto",
+  "tavily",
+  "exa",
+  "linkup",
+  "parallel",
+  "firecrawl",
+  "you",
+  "keenable"
+]
  6. Changed1 schema field changedv0.9.0
    • changedInput schema / properties / provider / enum
      Previous value: -[
-  "auto",
-  "tavily",
-  "exa",
-  "linkup",
-  "firecrawl",
-  "you"
-]New value: +[
+  "auto",
+  "tavily",
+  "exa",
+  "linkup",
+  "parallel",
+  "firecrawl",
+  "you"
+]
  7. Addedv0.8.0
  8. Removedv0.7.0
  9. Addedv0.2.1

TDQS

B3/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose real behavior: bounded page text, truncation warnings, stored-content references, and a compact-by-default response. It says nothing about provider fallback/rate limits, JS-rendering requirements, failure modes, or what 'source-only' excludes, which matters for a 9-param fetch tool.

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?

Three short sentences, front-loaded with purpose then return behavior then the detail toggle. No padding, though the 'complete v3 contract' phrasing is vendor jargon that spends words without adding actionable meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description's sketch of return values (bounded text, truncation warnings, stored-content references) is genuinely load-bearing. Against nine parameters, no annotations, and low schema coverage, however, the definition still leaves too much behavior and parameter meaning unstated to be called complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 44%, and the description only elaborates on 'detail' (already documented in the schema) plus the provider count. It leaves format, spans, spans_query, render_js, include_images and include_raw_html unexplained, so it does not compensate for the coverage gap.

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?

Names a specific verb and resource: 'Source-only URL extraction through 9 Web Search Plus v3 providers.' An agent can distinguish it from web_search because it extracts from given URLs rather than discovering them, though the phrase 'source-only' is somewhat opaque and the sibling is never named.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use statement and no mention of web_search as the alternative for discovery. The only signal is the implication that the tool operates on a caller-supplied URLs list.

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

Deploy Server

Other Tools