Specky

Research Questions

sdd_research

Transforms a list of research questions into a structured RESEARCH.md file with entries for findings, sources, recommendations, and status.

Instructions

Takes an array of research questions, generates RESEARCH.md with structured entries (question, findings placeholder, sources, recommendation, status), and writes it to the feature directory.

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": {
      "questions": "<questions>"
    },
    "name": "sdd_research"
  }
}

Input Schema

Name	Required	Description	Default
`spec_dir`	No	Spec directory path (relative to workspace root)	.specs
`questions`	Yes	Array of research questions to investigate and resolve
`feature_number`	No	Feature number (zero-padded, e.g. '001')	001

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.4.0-rc.14May 3, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations indicate non-read-only and non-destructive behavior, and the description adds that the tool writes a file. However, it does not specify whether it overwrites existing RESEARCH.md or appends, nor does it disclose any side effects. This is adequate but leaves ambiguity about file creation behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that conveys the input, output, and action without redundancy. Every word is functional, and the most critical information is front-loaded. No wasted space.

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

Completeness3/5

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

The description explains the output structure (question, findings placeholder, etc.) but does not map 'feature directory' to the spec_dir parameter or mention prerequisites like existing directory. Given the tool's simplicity and no output schema, the description is minimally complete but lacks contextual details for error handling or path resolution.

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?

Input schema covers all three parameters (feature_number, spec_dir, questions) with descriptions, achieving 100% coverage. The description adds no new meaning beyond stating that questions are an array, which is already in the schema. While consistent, it does not enhance the agent's understanding beyond 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?

The description clearly states the tool takes an array of research questions, generates a RESEARCH.md file with structured entries, and writes it to the feature directory. It specifies the verb ('takes', 'generates', 'writes'), the resource (RESEARCH.md with specific fields), and the action, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, nor does it mention when not to use it. Without any usage context or exclusions, agents may misuse the tool for tasks better suited to siblings like sdd_write_spec or sdd_generate_docs.

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

Deploy Server