Skip to main content
Glama

Start a research run (billed)

research

Run multi-turn web investigations to compare options, build datasets, or enrich records; these agentic runs take minutes, incur costs, and require a configured provider key.

Instructions

Start an agentic research run: many turns of searching and reading, which takes MINUTES and bills for the run. For comparisons, datasets or enriching records; a lookup is search's. After 25s it returns a handle: poll research_status, since calling this again pays for a second run. NOTHING IS CONFIGURED FOR THIS METHOD on this machine, so every call will fail. A key in one of LINKUP_API_KEY, NIMBLE_API_KEY, PARALLEL_API_KEY, PERPLEXITY_API_KEY, YOU_API_KEY turns it on: see load_env.

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": "research"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesThe question, or the instructions for the run.
effortNoHow much work the run should do -- and how much it costs. 'max' can take an hour.
providerNo
output_schemaNoJSON Schema the answer must conform to. Omit it to get prose instead.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A4.4/5.0
Behavior4/5

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

Goes well past the annotations by disclosing latency (minutes, 25s before a handle returns), billing per run, the cost of duplicate calls, and a hard prerequisite failure mode — nothing is configured on this machine and API keys via `load_env` are required. The only soft spot is that it doesn't describe how partial or failed runs surface, though `research_status` is named as the observation path.

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 action, then the cost/latency warning, then the gating prerequisite — the ordering matches decision priority. It is dense and every clause carries information, though the mid-sentence alternative clause ("a lookup is `search`'s") and the shouted capability warning are slightly harder to parse than they need to be.

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 billed, non-idempotent, open-world run with no output schema, it covers what an agent needs: cost, duration, the handle-then-poll pattern, and the fact that the tool is currently unusable without an env key. Nothing material about calling it correctly is missing.

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 75% and the schema already documents `query`, `effort` and `output_schema`, so the baseline applies. The description reinforces the cost dimension of `effort` ("bills for the run") but adds no syntax, defaults, or meaning for the undocumented `provider` enum, so it does not clearly exceed the schema.

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 ("Start an agentic research run") plus its defining traits: many turns of searching and reading, takes minutes, billed. It also explicitly contrasts with the sibling `search` ("a lookup is `search`'s"), so an agent can route correctly without opening another 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?

Gives concrete when-to-use cases (comparisons, datasets, enriching records) and the when-not case (simple lookups belong to `search`). It also prescribes the follow-up flow: poll `research_status` rather than calling again, with the reason spelled out (a second run, a second charge).

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