Skip to main content
Glama
Brilliant MCP

Brilliant MCP

Official

list_projects

Read-onlyIdempotent

List every project you own with key, backing, open state, canvas count, and publish details, so you can pass a name or key to init or canvas tools to work in any project, including closed ones.

Instructions

List every project this user owns, each with its display name, key (a folder path or brilliant-cloud:// key), backing (local/synced/cloud), open state (active tab / background tab / closed), canvas count when known, and whether it is published, with its url, visibility, audience and your role where known. Pass a name or key from this list as the project argument on init or any canvas tool to work in a project other than the one on screen, including a closed one.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_projects"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.10

TDQS

A4.5/5.0
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, so the safety profile is covered. The description adds value beyond that by disclosing the return shape (including runtime state like active/background/closed tab and conditional fields "when known"), which matters more than usual because there is no output schema. It stops short of stating scope limits, e.g. whether only owned projects appear or shared ones are included.

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-loaded with the verb and resource, then the full field list, then the actionable follow-up. Dense but every clause carries information; the long inline enumeration of returned fields is slightly heavy for a single sentence but is not padding.

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?

With no output schema and no parameters, the description carries the burden of describing the result, and it largely does. The remaining ambiguity is scope (owned-only vs. shared projects) and whether large project lists are truncated, which an agent would want to know before relying on it as an enumeration.

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?

Zero input parameters, so the baseline is 4. The description goes further by explaining how the returned name/key values are consumed by other tools, effectively documenting the output-to-input contract even though no parameter exists to describe.

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 ("List every project this user owns") and enumerates exactly what each entry contains: display name, key, backing store, open state, canvas count, publication status with url/visibility/audience/role. This is far more specific than a bare 'list projects' and lets an agent know precisely what it gets back.

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

Usage Guidelines5/5

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

Explicitly tells the agent what to do with the result: "Pass a name or key from this list as the `project` argument on `init` or any canvas tool to work in a project other than the one on screen, including a closed one." It names concrete downstream consumers and disambiguates the on-screen vs. other-project case, which is the key selection question here.

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