PrismSearch

Web Search

web_search

Read-onlyIdempotent

Search the web across multiple engines with automatic engine selection and fallback, returning titles, URLs, and snippets for any query.

Instructions

Search the web across multiple engines (Google, Bing, Brave, Baidu, DuckDuckGo, Sogou, 360, Yandex) with automatic engine selection and fallback. Returns titles, URLs and snippets.

Input Schema

Name	Required	Description	Default
`mode`	No	fallback: one engine, switch on failure (default). aggregate: query 2-3 engines concurrently and merge results by rank fusion	fallback
`page`	No	Page number (1-10)
`count`	No	Number of results (1-50)
`query`	Yes	Search keywords
`engine`	No	Search engine to use; auto-selected (with fallback) if omitted
`region`	No	Region code, e.g. cn, us, hk
`language`	No	Language code, e.g. zh-CN, en
`timeRange`	No	Only return results published within the past day/week/month/year (engines without support ignore it and add a warning)
`safeSearch`	No	Enable safe search

Output Schema

Name	Required	Description	Default
`page`	Yes
`cached`	Yes
`engine`	Yes
`engines`	No
`hasMore`	Yes
`results`	Yes
`warnings`	No
`searchTime`	Yes
`totalResults`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 29, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond that: automatic engine selection with fallback, and the shape of returned results. Rate limits and per-engine quirks are left to the schema.

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

Conciseness5/5

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

Two tight sentences, front-loaded with the core action and engine scope, then the return shape. No filler or redundancy.

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 needn't be explained, and the description still names titles/URLs/snippets. With full schema coverage and thorough annotations, the only gap is the missing routing guidance against sibling tools.

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% with rich per-parameter descriptions including the fallback/aggregate mode semantics, so the schema already carries parameter meaning. The description adds nothing about parameters beyond restating the engine list, making baseline 3 appropriate.

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 ('Search the web across multiple engines') and enumerates the supported engines, so the agent knows exactly what the tool does. It does not explicitly contrast with siblings like image_search or fetch_page, leaving differentiation implicit.

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?

Usage is implied by the name and engine list, but there is no explicit 'use this when...' guidance and no mention of when to prefer fetch_page, image_search or wechat_search. The agent must infer the routing decision itself.

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

Deploy Server