Skip to main content
Glama

Start a design research session

inspo_start

Start a design-research session for a website or app idea by creating a project workspace for screenshots and votes and launching the local voting board.

Instructions

Start a new design-research session for a website/app idea. Creates /.inspo// where screenshots and votes live, and starts the local voting board. Call this first, after you have analyzed the idea and (if any) the existing app.

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": {
      "idea": "<idea>"
    },
    "name": "inspo_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
copyNoReal draft copy for the product (in the user's language). Used to render every style specimen.
ideaYesThe idea in the user's words, plus your one-paragraph read of it (product, audience, tone).
titleNoShort project name, e.g. "Tueste coffee club".
contextNo
sectionsNoPage sections to research, in page order. Agree on them with the user first (see inspo_sections).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does disclose real behavior: it writes a project-scoped directory holding screenshots and votes, and launches a local voting board (a long-running process). It omits failure modes such as calling twice or how to stop the board, but the mutation and server side effects are disclosed.

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?

Three short sentences with zero waste: purpose first, then side effects, then ordering. The most decision-relevant constraint ("Call this first") is placed at the end where it reads as an instruction, not buried mid-text.

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?

For a five-parameter tool with deep nested objects and no output schema, the definition covers purpose, side effects and call ordering well. The remaining gap is what the call returns (session id, board URL) and whether re-invocation creates a second session.

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 80%, so the schema already documents idea, title, copy, context and sections in detail. The description only lightly reinforces this by noting the idea analysis and existing app should precede the call; it adds no new meaning about the nested copy or sections payloads.

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 a new design-research session") plus two concrete side effects: creating <project>/.inspo/<id>/ and starting the local voting board. The phrase "Call this first" positions it clearly against siblings like inspo_analyze and inspo_sections.

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

Usage Guidelines4/5

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

Gives an explicit prerequisite ordering: call it first, after analyzing the idea and any existing app. It does not name the analyzing tool directly or state what to do if a session already exists, but the when-to-use context is clear.

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