search-mcp

Web search

web_search

Read-onlyIdempotent

Search the web for current, time-sensitive information such as news, weather, prices, or recent events; returns result titles, URLs, and snippets instead of full pages.

Instructions

Search the web for CURRENT information: news, current events, anything recent/latest/today/this week, weather, prices, time-sensitive facts. Do NOT use for general knowledge like recipes, definitions, or history — those have better tools. Returns snippets (title, url, snippet), not full pages.

    Args:
        query: what to search for, sent to the search engines exactly as written.
        max_results: how many results (default 10, allowed 1-25).
        region: optional region code `country-lang`, e.g. "us-en", "es-es", "de-de"; default "wt-wt" (no region).

Input Schema

Name	Required	Description	Default
`query`	Yes
`region`	No
`max_results`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 29, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description's added value is in return shape: 'Returns snippets (title, url, snippet), not full pages.' That is a genuinely useful capability limit — the agent knows it cannot get page content here. It doesn't mention rate limits or result quality/failure modes, keeping it short of a 5.

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 purpose and exclusions, then a compact Args block for the three parameters — no filler sentences. The Args formatting is slightly verbose relative to the description's otherwise terse style, but every element carries information.

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

Completeness5/5

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

For a 3-parameter read-only search tool with no output schema, the description supplies return format, parameter constraints, and default behavior. Nothing needed to invoke it correctly is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden and does so: query is sent verbatim to the search engines, max_results has a default of 10 and a hard range of 1-25, and region has a concrete `country-lang` format with examples and the 'wt-wt' default. Each parameter's semantics and constraints are documented beyond the bare types.

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 (search) and resource (the web) plus the information class it serves: news, current events, weather, prices, time-sensitive facts. It also explicitly carves out what it is NOT for (recipes, definitions, history), so the agent can route correctly even without siblings.

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

Usage Guidelines5/5

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

Gives explicit use conditions (recent/latest/today/this week) and explicit exclusions ('Do NOT use for general knowledge like recipes, definitions, or history — those have better tools'). That is a full when/when-not statement with a pointer to alternatives.

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

web_searchA