Skip to main content
Glama

Publish the design direction

inspo_brief

Save the converged design direction to the board's Brief tab and DESIGN.md with concept, palette, type, components, references, do/don't, and tokens.

Instructions

Save the final design direction to the board's Brief tab and to .inspo//DESIGN.md: concept, principles, palette, type, components picked, references, do/don't, and tokens. Call once the user has converged.

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": {
      "name": "<name>",
      "summary": "<summary>"
    },
    "name": "inspo_brief"
  }
}

Input Schema

NameRequiredDescriptionDefault
doNo
dontNo
nameYesName of the direction.
fontsNo
paletteNo
sessionNoSession id. Defaults to the most recent session in this project.
summaryYes
sectionsNoPage outline, top to bottom.
tokensCssNo:root { ... } CSS custom properties.
componentsNoComponent ids (lib-* or c-*) to build.
principlesNo
referencesNoItem ids that define the direction.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden and does well to disclose dual persistence (board Brief tab plus a filesystem markdown file), which signals a durable write. It does not say whether an existing brief is overwritten, whether the write is reversible, or what happens if the session is invalid, leaving key mutation semantics unstated.

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?

Two sentences, front-loaded with the action and destinations, then the field list, then the timing rule. The field enumeration is long but functional; it partially restates schema property names, which keeps it just short of maximally efficient.

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?

For a 12-parameter write tool with no annotations and no output schema, the description covers purpose, targets, content, and timing, which is substantial. It omits what the call returns (brief id, file path, or created/updated status) and overwrite/repeat-call behavior, gaps that matter for a publish step.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%, so the description must compensate, and it largely does: 'principles, palette, type, components picked, references, do/don't, and tokens' map cleanly onto principles, palette, fonts, components, references, do/dont, and tokensCss. 'sections' (page outline) and 'session' are not mentioned, and required fields name/summary are only loosely covered by 'concept'.

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?

States a concrete verb ('Save') and a well-defined resource ('the final design direction') and names both destinations: the board's Brief tab and .inspo/<id>/DESIGN.md, so the agent knows exactly what artifact is produced. It stops short of distinguishing itself explicitly from siblings like inspo_export_pdf or the incremental inspo_add_* tools, which also persist design content.

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?

'Call once the user has converged' gives a clear trigger condition: this is the terminal publish step after exploration, not an incremental edit. There is no explicit when-not or named alternative for partial/iterative saves, leaving the agent to infer that inspo_add_styles and similar are the fallback.

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