Skip to main content
Glama

Brilliant Design (hosted)

See a Brilliant design

inspect_design
Read-onlyIdempotent

Use this when the user wants to see, check or talk about a Brilliant design opened in this conversation: it returns the element tree as Blueprint rows with ids (the ids rows can target), how each turn of the design ended (complete, halted, stopped at a limit, or still building) and any rows that did not apply. With wait, it holds up to 25 seconds for the design's latest turn to end; a turn still building at that point answers its progress. A design renders once the user has the canvas open in the chat.

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": {
      "seed": "<seed>"
    },
    "name": "inspect_design"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedYesThe design's slug (from the design result).
waitNotrue holds the answer up to 25 seconds for the design's latest turn to end. Default false.

Output Schema

NameRequiredDescriptionDefault
atNo
slugYes
turnYes
ageMsNo
causeNo
staleNo
turnsNo
resultNo
statusYes
outcomeNo
elementsNo
latestTurnNo
diagnosticsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, and the description adds meaningful behavior on top: the shape of the returned rows, the four possible turn outcomes (complete, halted, stopped at a limit, still building), and the canvas-open precondition for rendering. The 25-second hold semantics of `wait` are spelled out, including the fallback of returning progress when a turn is still building. Minor gap: no mention of what happens with an invalid or stale seed.

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?

Front-loads the usage trigger before the payload details, and every clause carries information. Slightly dense run-on construction (one long colon-headed sentence covering returns, timing, and preconditions) costs a point versus a cleanly segmented version.

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 read tool with annotations, a full schema, and an output schema, the description covers purpose, timing/latency semantics, return structure, and the rendering precondition. Error paths (bad seed, design not found, canvas not open at call time) are unaddressed but are the only notable omission.

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 100%, so both parameters are already fully documented, and the description largely restates the `wait` behavior (up to 25 seconds) that the schema already declares. It adds one nuance beyond the schema — that a still-building turn answers with its progress rather than blocking further — and clarifies that returned ids are the ones rows can target, which is worth noting but thin given how complete the schema is.

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 specific verb and resource ("see, check or talk about a Brilliant design opened in this conversation") and enumerates what comes back: the element tree as Blueprint rows with ids, per-turn end states, and inapplicable rows. Distinct enough from a design-creation tool, though it never names edit_design as the path for changes, so the read-vs-mutate boundary is inferred rather than stated.

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 clear triggering context (user wants to see/check/discuss an existing design in this conversation) and a scoping precondition ("a design renders once the user has the canvas open in the chat"). It stops short of explicit exclusions or naming an alternative tool for when the user wants to modify rather than inspect.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources