Skip to main content
Glama
Sign In
Research Toolkit

Research Toolkit

by rrrrrredy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

research_start

Start or complete a research task brief, returning the task directory and stage guidance so agents can run structured research with clear scope and evidence standards.

Instructions

Create a research task or complete its missing brief. Returns its directory and stage guidance. language accepts "en" (English), "zh" or "zh-CN" (the same Chinese methods); checked before task records are written. Assemble concrete coverage and expected results from context; brief uses question, audience, scope, output, depth and evidence_standard. Returned clarification_questions guide the agent; do not forward them as a questionnaire. Explain consequential alternatives and resolve critical choices with the user. Use the complete shared research methods. Omit profile; it is retained only for older clients and saved tasks. Resume saved materials through research_status; historical receipts remain unchanged. New work uses independent host review, audit and acceptance. review_readiness defaults to host_native.

Input Schema

NameRequiredDescriptionDefault
taskYes
briefYes
profileNofull
languageNoen

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / properties / profile / enum
      Removed value: -[
-  "lite",
-  "full"
-]
  2. First observedv1.1.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it notes language is checked before records are written, that clarification_questions should guide the agent rather than be forwarded, that profile is ignored, and that review_readiness defaults to host_native. Some phrasing ('complete shared research methods', 'historical receipts remain unchanged') is opaque rather than informative.

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?

The core purpose is front-loaded, but the body is a series of terse fragments with uneven flow; several sentences ('Use the complete shared research methods') are cryptic rather than economical. Moderate cleanup would improve it.

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

Completeness4/5

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

An output schema exists, so return values needn't be described. Given a nested brief object and 4 params, the description covers the brief structure, language, profile deprecation and reviewer behavior reasonably; the only real gap is the undocumented 'task' param.

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 coverage is 0%, so the description must compensate. It does well for language (en/zh/zh-CN) and the nested brief fields (question, audience, scope, output, depth, evidence_standard) and deprecates profile, but the required 'task' parameter gets no explanation at all.

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?

The first sentence gives a specific verb and resource ('Create a research task or complete its missing brief') and adds a return-value note ('Returns its directory and stage guidance'). It is distinguishable from research_status for resuming, though it doesn't sharply differentiate from research_save or research_guide.

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?

It routes one clear case ('Resume saved materials through research_status') and deprecates profile, but most sibling relationships (research_review, research_save, research_finish) are left implicit. The agent must infer which tool handles mid-task steps.

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

Deploy Server

Other Tools