Skip to main content
Glama
Sign In
yeivily-mcp

yeivily-mcp

by yeib
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

web_search

Read-onlyIdempotent

Search DuckDuckGo for current information, documentation, or news outside training data; returns titles, URLs, and snippets, with optional deep text excerpts from top pages.

Instructions

Search the web (DuckDuckGo) for current information, documentation, news or anything outside your training data. Returns titles, URLs and snippets. Set deep=true to also get text excerpts from the top pages.

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": "web_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
deepNoAlso extract text from the top results (slower).
queryYesSearch query.
topicNogeneral
time_rangeNoOnly results from this period.
max_resultsNoResults to return (1-20).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly, openWorld and idempotent, so the safety profile is covered. The description adds real value beyond that: it discloses the return shape (titles, URLs, snippets) and flags that deep=true costs extra latency for page excerpts, which is the key behavioral tradeoff an agent must weigh.

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?

Three short sentences, front-loaded with the action and then the return contract and the one meaningful option. No filler or repetition, and the deep-mode caveat is placed after the primary purpose.

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?

For a read-only, no-output-schema search tool the description covers purpose, use cases, return shape and the main option, which is nearly everything an agent needs. It omits failure or rate-limit behavior, a minor gap for a scraped search backend.

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 80%, so the schema already documents query, topic, time_range, max_results and deep. The description only restates the deep flag ('text excerpts from the top pages'), duplicating the schema's 'Also extract text from the top results (slower)' with no new syntax, format or default guidance. Baseline 3 is 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') and names the backend (DuckDuckGo), plus concrete use cases (current information, documentation, news, anything outside training data). It does not explicitly contrast with the sibling fetch_page, but search-vs-fetch is inherently distinct enough for an agent to pick correctly.

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?

Clearly frames when to reach for this tool: whenever the answer isn't in training data and needs current web information. There are no explicit exclusions or pointers to fetch_page for reading a known URL, so it stops short of full when/when-not guidance.

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