Skip to main content
Glama
DeepSeek Search Everywhere MCP

DeepSeek Search Everywhere MCP

deepseek_check_research

Read-onlyIdempotent

Poll a running research job to get its report, page through sources for client-side synthesis, or submit a cited report for verification. Use with a job_id from starting research.

Instructions

Continue a research job: poll it, read its sources for client synthesis, or submit your report.

Free ($0.00); waits up to 45 s per call. Returns the finished report (status "done"), progress while the job runs ("running": call again with the same job_id) or job_not_found once it expired. For synthesis="client" jobs ("awaiting_report"), page= reads the next page of sources and report= submits your report with [id] citations for verification.

When NOT to use: to start research (deepseek_research). Never restart a running job; poll it.

Returns: {"ok": True, "status": "done"|"running"|"awaiting_report", "job_id": str, ...}.

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": {
      "job_id": "<job_id>"
    },
    "name": "deepseek_check_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage of sources to read for a synthesis='client' job (default None)
job_idYesUnique UUID identifier of the research job to poll (from deepseek_research)
reportNoReport with [id] citations to verify (synthesis='client' jobs only, default None)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv3.3.0
    • addedInput schema / properties / page
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Page of sources to read for a synthesis='client' job (default None)",
      +  "title": "Page"
      +}
    • addedInput schema / properties / report
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Report with [id] citations to verify (synthesis='client' jobs only, default None)",
      +  "title": "Report"
      +}
  2. Addedv3.0.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false), and the description still adds substantive behavior: zero cost, a 45-second wait ceiling, the three status values, the poll-again loop for "running", and job_not_found on expiry. One tension is left unaddressed: report= submits data into the job, which sits awkwardly against readOnlyHint=true, and the description does not explain how that is treated.

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, then behavior, then the exclusion, in a compact block with no filler sentences. It is slightly dense and the trailing returns sketch partially duplicates the output schema, but nothing is genuinely wasteful.

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?

For a three-parameter polling/continuation tool with an output schema and full annotation coverage, everything an agent needs is present: cost, timeout, status semantics, expiry handling, mode branches, and the sibling to use instead. No material gap remains.

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 coverage is 100%, so the baseline is 3, but the description earns above that by explaining the mode-gated meaning of page= (next page of sources for synthesis="client") and report= (citations in [id] form for verification) plus job_id's origin from deepseek_research. That is workflow meaning the schema does not convey.

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?

Opens with a specific verb plus resource ("Continue a research job") and enumerates the three things the tool can do in that mode: poll, read sources, submit a report. That framing makes it immediately distinguishable from deepseek_research, which starts jobs.

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?

Explicitly states the excluded case ("When NOT to use: to start research (deepseek_research)") and names the anti-pattern ("Never restart a running job; poll it"). It also tells the agent which parameters belong to which job mode (page= for reading sources, report= for submitting), so the branch conditions are unambiguous.

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