Skip to main content
Glama
Native Research MCP

Native Research MCP

by pipiwego

research_start

Read-only

Launch a research task by defining a goal and scope, with effort, domain, token, and time budgets to control how sources are gathered and how requests are spent.

Instructions

Start a research task with a goal and scope. Domain preferences do not restrict provider browsing. Budgets apply between requests.

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": {
      "goal": "<goal>",
      "scope": "<scope>"
    },
    "name": "research_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalYes
scopeYes
effortNolow
domainsNo
max_callsNo
domain_policyNoprefer
max_total_tokensNo
freshness_secondsNo
max_elapsed_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint, non-idempotent). The description adds real value beyond them by clarifying that domain preferences do not restrict provider browsing and that budgets are shared across subsequent requests rather than per call. It omits, however, whether the call returns immediately with a task handle and how progress should be observed, and it does not flag that repeated calls spawn separate tasks (consistent with idempotentHint=false but never stated).

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?

Three short sentences, front-loaded with the required inputs, with no filler. "Budgets apply between requests" is terse to the point of being cryptic, costing a little clarity.

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?

Nine parameters with 0% schema coverage and no output schema demand much more. The definition never says what the call returns (task handle/id), how to monitor it via research_status, or what each budget knob governs, which is a significant gap for an async task-launching tool.

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 0%, so the description must carry all parameter meaning, and it only partially does: it explains goal/scope, domains, domain_policy (implicitly, via "do not restrict provider browsing"), and the budget family. Effort, freshness_seconds, and the token/timeout budget parameters receive no explanation of their effect or tradeoffs.

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

Purpose4/5

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

"Start a research task with a goal and scope" gives a specific verb plus resource and names the two required inputs, so the action is unambiguous. It does not explicitly differentiate itself from research_status, research_evidence, or research_recover, which an agent must infer from the verb alone.

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?

The word "Start" implies this is the entry point of a workflow, but the description never states when to use it versus research_status (progress checks) or research_recover (resume). No prerequisites or exclusions are given, so usage is only implied.

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