Skip to main content
Glama
Sign In

Desearch

by io.github.Desearch-ai
OverviewDiscussionsAdmin

Search API

search-api
Read-only

Search the web with the Desearch Search API and return ranked pages, each with its title, URL, publication date when known, and the passage that best matches the query. Set page_text to add each page's full text. Returns { results, cost_usd, usage_count, service, currency }. Use search for titles and links only, and web-search for SERP-style snippets.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search-api"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo'fast' returns results sooner; 'balanced' (API default) favors relevance.
countNoNumber of results: 10 (API default), 15, or 20.
queryYesSearch query, example: 'Who won the 2024 Nobel Prize in Physics?'
end_dateNoOnly pages published on or before this date (YYYY-MM-DD).
page_textNoInclude each page's full text (API default false).
highlightsNoInclude the passage that best matches the query (API default true).
start_dateNoOnly pages published on or after this date (YYYY-MM-DD).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context beyond that: the exact return envelope ({ results, cost_usd, usage_count, service, currency }) and the effect of page_text on payload size.

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 sentences, front-loaded with the core action and return shape, then the page_text toggle, then the sibling routing. Dense but every sentence carries information; the return-envelope listing is slightly heavy but justified since there is no output schema.

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 no output schema, the description compensates by naming the return fields, and it covers the key optional behaviors (page_text, highlights default). It does not mention pagination or rate/cost implications beyond cost_usd, but for a 7-param read-only search tool this is close to complete.

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 description coverage is 100%, so every parameter is already documented in the schema, including mode, count, dates, page_text, and highlights. The description only restates page_text's effect ('add each page's full text') without adding format or interaction details, so the baseline 3 applies.

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 and resource ('Search the web with the Desearch Search API') and describes the return shape (ranked pages with title, URL, publication date, best-matching passage). It explicitly distinguishes itself from the siblings 'search' and 'web-search' by naming what each returns.

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?

Explicitly routes the agent: 'Use search for titles and links only, and web-search for SERP-style snippets,' which tells the agent when to pick an alternative. It does not state when this tool should be avoided in favor of ai-search or fetch, so it falls short of full when/when-not coverage.

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

All Desearch toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources