Skip to main content
Glama
Brilliant MCP

Brilliant MCP

Official

get_knowledge

Read-onlyIdempotent

Load design knowledge by key for Blueprint DSL or HTML design work; prerequisite docs are auto-bundled by default and can be skipped to request only named keys.

Instructions

Load design knowledge by key. Blueprint DSL work loads it first; an html fence needs none. Pass keys from the available keys list returned by init (e.g. "blueprint/core", "design/colors", "effects/glass"). By default a key also pulls in its prerequisite docs (its assumes: deps); the response names them under "Also auto-loaded" so you can see what was bundled. Pass includeDependencies: false to load ONLY the keys you name (the skipped prerequisites are listed so you can request them deliberately).

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": "get_knowledge"
  }
}

Input Schema

NameRequiredDescriptionDefault
keysNoList of knowledge keys to load. See available keys returned by init.
sessionIdNoSession ID for per-session tracking. Optional.
includeDependenciesNoWhether to auto-load each key's prerequisite docs (its `assumes:` deps). Default true. Set false to load exactly the keys you name and nothing else; the response lists the prerequisites it skipped so you can request them explicitly.

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 readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds the non-obvious behavior that keys auto-pull `assumes:` prerequisites, that the response surfaces them under "Also auto-loaded", and what includeDependencies:false changes. It does not cover failure behavior for unknown keys or whether init must be called first, which keeps it short of a 5.

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?

Purpose is front-loaded in five words, then workflow rule, then key sourcing, then the dependency toggle. Every sentence carries information, though the parenthetical key examples and the includeDependencies explanation partially duplicate the schema.

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, the description usefully explains what the response contains (bundled prerequisites, skipped prerequisites). Gaps remain around error handling for bad keys and the hard dependency on init, but for a 3-parameter read tool with full annotation coverage this is close to complete.

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 description coverage is 100%, so the baseline is 3; the description still adds provenance for `keys` (take them from the list returned by init) and concrete example keys, which the schema only partially repeats. The includeDependencies explanation largely restates the schema text, limiting extra value.

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?

"Load design knowledge by key" gives a specific verb and resource, and the following sentence scopes it to Blueprint DSL work while explicitly excluding html-fence work. An agent can tell this apart from init (which produces the keys) and from the html/svg generation siblings without opening any schema.

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?

It states both when to call it (Blueprint DSL work loads it first) and when not to (an html fence needs none), plus the prerequisite that keys come from init's available-keys list. That is explicit routing logic rather than implied usage.

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