Skip to main content
Glama
Sign In
deepseek-search

deepseek-search

by BryleXia
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

DeepSeek Web Search

deepseek_search
Read-only

Search the live web for ranked results with snippets, summaries, dates, authority, and relevance scores; use operators and recency filters for Chinese-language and China-focused research.

Instructions

Search the live web with DeepSeek's search engine. Returns ranked results with title, URL, snippet, long summary, publish date, site name, authority (0-4; >=3 highly authoritative), and relevance score (0-3; >=1.5 high quality).

Query limits and operators:

  • Query is limited to 128 Unicode characters; longer queries are truncated with a warning.

  • site:example.com, -site:example.com, -word, "exact phrase", -"phrase", lang:zh,en, after:YYYY-MM-DD, before:YYYY-MM-DD.

Guidance:

  • Best for Chinese-language and China-focused queries; pair it with another provider for English technical documentation.

  • need_content=false by default; use deepseek_fetch on selected URLs when full page text is needed.

  • Empty results are a normal successful search, not an error.

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 (1-50). Each result includes a 600-800 character summary; higher counts use more context.
queryYesSearch query (1-4096 chars; truncated to 128 Unicode chars before sending). Supports operators: site:example.com, -site:example.com, -word, "exact phrase", -"phrase", lang:zh,en, after:YYYY-MM-DD, before:YYYY-MM-DD.
freshnessNoRecency filter mapped to after:YYYY-MM-DD. Ignored if query already contains after:/before:.noLimit
need_contentNoReturn full page content per result. Expensive in tokens; prefer deepseek_fetch on selected URLs.
ori_questionNoOptional original user question (truncated to 128 chars) to improve query understanding.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.2

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, destructiveHint=false, and idempotentHint=false, so the safety profile is covered. The description adds real behavioral context beyond them: 128-character truncation with a warning, the authority (0-4) and relevance (0-3) score scales, and the fact that zero results is still a successful call. It does not discuss rate limits, latency, or pricing beyond the token-cost note, so it is strong but not exhaustive.

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 purpose and return format, then neatly sectioned into query limits and guidance, which is easy for an agent to scan. It loses a little to redundancy: the full operator syntax is duplicated from the input schema and could have been referenced instead of restated.

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?

With no output schema, the description correctly compensates by explaining the result fields and their score scales, and it covers cost, truncation, and empty-result behavior for a five-parameter read tool. An agent has everything needed to call it correctly and interpret what comes back.

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 all five parameters are already documented, and the description's operator list is a near-verbatim repeat of the query parameter's schema text. The genuinely additive bits, the truncation warning and the recommendation to prefer deepseek_fetch over need_content, are already present in the schema descriptions as well. Baseline 3 is appropriate.

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 live web with DeepSeek's search engine") and immediately enumerates the return shape (title, URL, snippet, summary, publish date, site name, authority, relevance). It also names the sibling deepseek_fetch, so an agent can place it relative to the other tool without opening a schema.

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?

Explicit about when this source is preferred ("Best for Chinese-language and China-focused queries") and when to pair it with another provider (English technical documentation). It also routes the agent to deepseek_fetch when full text is needed and preempts a common misread by stating that empty results are a normal success, not an error.

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