Skip to main content
Glama
Native Research MCP

Native Research MCP

by pipiwego

deepseek_search

Read-only

Extend research tasks by stating missing evidence and running targeted web queries, with refresh options to verify new results instead of cached ones.

Instructions

Extend the task with native web research. State the missing evidence. Set refresh for new verification instead of a cached result.

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": {
      "research_id": "<research_id>",
      "parent_revision": "<parent_revision>",
      "gap": "<gap>",
      "query": "<query>"
    },
    "name": "deepseek_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
gapYes
queryYes
refreshNo
research_idYes
parent_revisionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, non-idempotent and non-destructive, so the safety profile is covered. The description adds one genuinely new behavioral fact: results may come from a cache unless refresh is set. It says nothing about result shape, result volume, or latency, which matters because there is no output schema to fall back on.

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

Conciseness3/5

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

Three short, front-loaded sentences with no filler, so nothing is wasted. The tradeoff is that the telegraphic style ("State the missing evidence") is elliptical enough to require interpretation about who states it and in what form.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter, four-required tool with zero schema coverage and no output schema, the definition leaves too much unexplained: the research_id/parent_revision revision chain is never addressed, and the agent gets no notion of what comes back from a search. Only the refresh behavior and the vague notion of a gap are covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for five parameters with four required, yet the description supplies real semantics for two of them: gap is what names the missing evidence, and query is the search itself, with refresh meaning new verification versus cache. It leaves research_id and parent_revision entirely unexplained, but given the total absence of schema documentation the text adds substantial meaning over the bare field names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Extend the task with native web research" conveys a search-performed-on-behalf-of-a-research-task, so the general action is inferable, but the phrasing is indirect and never states plainly that this performs a web search. It also does not distinguish the tool from siblings like deepseek_read_url or research_evidence, which an agent could plausibly reach for.

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?

"State the missing evidence" implies the tool is used when a specific evidence gap exists, which is a workable usage cue, and the refresh sentence gives conditional guidance on that parameter. However, there is no explicit when-not guidance, no named alternative for fetching an already-known URL, and no prerequisites such as needing an existing research_id.

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