Skip to main content
Glama

Linkup deep research (start task)

linkup-research

Runs autonomous multi-source research for questions a single search cannot resolve, returning verified findings with citations and an audit trail.

Instructions

Start an autonomous research task with Linkup (POST /v1/research). Asynchronous: returns at once with id and status "pending"; the agent then plans, searches many sources in parallel, verifies and synthesises, in 2 to 20 minutes. Collect the result with linkup-wait-research (polls for you) or linkup-get-research.

Price per task by reasoning_depth: S 0.25 USD (2 to 5 min), M 0.50 (3 to 7 min),
L 1.50 (5 to 10 min, the default), XL 2.50 (10 to 20 min). Failed tasks are not billed.
Do not create a second task to "retry" a slow one; wait on the id you have.

Use it for questions a single search cannot resolve: verified answers with an audit trail
of citations, a focused investigation of one subject, or a broad report by theme. For a
quick fact use linkup-search. Set mode explicitly for predictable latency, cost and
shape. Phrase the question precisely: angles to cover, leads to pursue, facts to verify,
entities to compare, constraints, and the structure you expect back. Put dates in
from_date/to_date, give a few trusted include_domains when they exist.

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": "linkup-research"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoanswer: precise, evidence-backed answer with a definitive solution. investigate: focused report on one defined subject. research: structured report by theme over many topics or entities in parallel. Omit (API default auto) to let the agent classify the question.
queryYesThe research question, precise and complete (see tool description).
to_dateNoYYYY-MM-DD, sources on or before this date.
from_dateNoYYYY-MM-DD, sources on or after this date.
output_typeNosourcedAnswer: natural-language answer with citations and a sources list. structured: JSON matching structured_output_schema (keep it flat; nested arrays of objects raise latency and failure rate).sourcedAnswer
exclude_domainsNoDomains to exclude.
include_domainsNoRestrict sources to these domains (up to 100). Strongly recommended when authoritative sources are known: better quality, lower latency.
reasoning_depthNoS light, M balanced, L thorough (default), XL exhaustive. Higher depth does not mean a longer answer, it means more coverage.L
structured_output_schemaNoRequired when output_type is structured. JSON Schema (object or string), root type object.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (which only state non-read-only, open-world, non-idempotent, non-destructive), the description discloses the asynchronous contract (immediate return with id and pending status), the 2-20 minute runtime band, per-task pricing by reasoning_depth with per-tier latency, and that failed tasks are not billed. That is exactly the behavioral context an agent needs before committing to a costly long-running call.

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 the core operation and return shape, then cost, then when-to-use, then query-shaping advice — a sensible ordering. It is dense but nearly every sentence carries actionable information; the pricing table is verbose in prose form but earns its space by driving depth selection.

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 9-parameter, async, paid, open-world task starter with no output schema, the description covers the return contract (id + pending status), how to collect results, latency expectations, cost tiers, retry behavior, and query construction. Nothing material is missing for correct invocation.

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 100%, so the baseline is 3, but the description adds genuine guidance beyond the schema: how to phrase the query (angles, leads, facts to verify, entities to compare, constraints, expected structure), putting dates in from_date/to_date, supplying a few trusted include_domains, and setting mode explicitly for predictable latency, cost and shape. It does not restate the enum meanings, which is correct since the schema already does.

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?

The description names a specific verb and resource ('Start an autonomous research task', POST /v1/research) and immediately distinguishes the tool from siblings by pointing to linkup-search for quick facts and linkup-wait-research / linkup-get-research for retrieval. An agent can tell exactly what this tool does and does not do without opening any 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 when-to-use cases are given ('questions a single search cannot resolve: verified answers with an audit trail, a focused investigation, a broad report by theme'), along with a named alternative for the simple case (linkup-search). It also gives an explicit anti-pattern: do not create a second task to retry a slow one, wait on the id you have.

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