Skip to main content
Glama

Search design system

figma_local_search_design_system
Read-only

Search a Figma file and team libraries for design system components, variables, and styles using multiple queries in one call, returning ordered matches for each asset type.

Instructions

Search for design system assets (components, variables and styles) in the file and in the team's libraries. Pass queries as an array of objects, each with entity ("component", "variable" or "style") and a string query, e.g. {"fileKey":"","queries":[{"entity":"component","query":"button"},{"entity":"variable","query":"surface"}]}. Combine the searches the task needs in one call. Results come back in a results array in the same order as queries.

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": {
      "fileKey": "<fileKey>",
      "queries": "<queries>"
    },
    "name": "figma_local_search_design_system"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum matches per query. Defaults to 10.
fileKeyYesThe key of the Figma file to use. If a URL is provided, extract the file key from it: for https://figma.com/design/:fileKey/:fileName?node-id=1-2 the fileKey is `:fileKey`. For https://figma.com/design/:fileKey/branch/:branchKey/:fileName use the branchKey. A full URL is also accepted.
queriesYesArray of search objects. Results are returned in the same order.
disableCodeConnectNoAccepted for compatibility; this server does not attach Code Connect data to search results.
includeLibraryKeysNoRestrict results to these library keys (library file keys, as returned by figma_local_get_libraries or earlier results).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds context beyond them: it is read-only across both the file and team libraries, and results return in a `results` array in the same order as `queries` – valuable since there is no output schema. It does not contradict the annotations.

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?

Three sentences, front-loaded with purpose, then usage, then return shape, with no filler. The embedded JSON example is slightly long relative to what the schema already conveys, which keeps it from a 5.

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 5-parameter read-only search with no output schema, the description covers purpose, batching, and result ordering, which is what an agent needs to call it correctly. Minor omissions such as the default per-query limit are handled by the schema itself.

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 100%, so each parameter is already documented, and the description's worked JSON example largely restates the entity enum and query pairing from the schema. The one real addition is the ordering guarantee between `queries` and `results`, which the schema only hints at, so baseline 3 fits.

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?

The description uses a specific verb ('Search') with an enumerated resource set (components, variables, styles) and states scope ('in the file and in the team's libraries'). It is clear what the tool returns, but it never distinguishes itself from siblings like figma_local_get_variable_defs or figma_local_get_libraries, which overlap conceptually.

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

Usage Guidelines3/5

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

'Combine the searches the task needs in one call' is a genuine batching guideline, and the mention of figma_local_get_libraries for library keys gives a light workflow hint. However, there is no explicit when-to-use/when-not versus the sibling variable, library, or design-context tools, so routing is only implied.

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