Skip to main content
Glama

DeepSeek Web Search

deepseek_search

Search the web through DeepSeek's Search API to retrieve titles, URLs, snippets, dates, and source authority. Use search operators to target queries and refine results.

Instructions

Search the web with DeepSeek's Search API. Returns titles, URLs, snippets/summaries, dates and source authority. Supports search operators and an original-question hint.

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": "deepseek_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNoNumber of results to request (1-50). Default 10.
queryYesSearch query, 1-128 characters. Supports site:/ -site:, -term, "exact phrase", lang:, after:, before:.
localizationNoOptional IP/locale hint used for localized results.
need_contentNoAsk the API to include page content in results (heavier response).
ori_questionNoOriginal user question, truncated to 128 characters. Sent as ori_question to improve recall.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations at all, the description carries the full burden, and it does disclose meaningful behavior: the shape of returned results (titles, URLs, snippets, dates, source authority) and that an original-question hint improves recall. It says nothing about authentication, rate limits, cost/latency of an external API call, or truncation/pagination of results.

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 followed by output shape and capabilities; no filler. The final sentence is mildly redundant with the schema's operator documentation, which keeps it from a 5.

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?

For a simple 5-parameter read tool with no output schema, describing the return fields fills a real gap, and that is present. However, with zero annotations the definition should still say something about the external-call nature (credentials, latency, limits) to be fully self-sufficient.

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 baseline is 3. The description adds only a light gloss — that search operators are supported and that ori_question is an 'original-question hint' — which is already spelled out in the parameter descriptions.

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 with DeepSeek's Search API") and adds the concrete return fields, so an agent knows exactly what it gets. It does not explicitly contrast with siblings like deepseek_fetch, so it stops short of full differentiation.

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 only implied by the verb 'search the web' — there is no explicit when-to-use or when-not-to-use, and no pointer to deepseek_fetch as the alternative when a URL is already known. An agent can infer the split from names, but the description itself provides no routing guidance.

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