Skip to main content
Glama

Search components

search_components
Read-only

Searches the components of every package assigned to the project by use case, behavior, or description, and returns up to 10 ranked matches with a relevance score. Read-only. Use it when you can describe what the UI must do but do not know the component name. The query is free-text describing the need, such as "date range picker" or "dismissible inline warning" - not a component name, not a glob, and not a props expression. Do not use it when the exact name is known (get_component is direct and returns the full spec) or when you want the complete catalog (list_components). Semantic ranking needs AI features on the Team plan or above; on other plans it falls back to name and import-path matching and the score is null. No close match returns an empty result list, not an error. Null scores or no results do not mean the component is missing: in that mode a use-case phrase often matches nothing, so choose from list_components by name and use note, or retry with a plain component word such as "button".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesFree-text description of the need - a use case, behavior, or purpose, e.g. "date range picker". Not a component name and not a glob.
project_idYesUUID as returned by list_projects - not the project name, title, or slug, and not guessable. Fetch it once and reuse the same id across tools. An id outside the caller's organization returns "Project not found or access denied" rather than empty data, and a project withheld by a plan limit returns a plan error that retrying cannot clear. It bounds the search to the packages assigned to this project, so the same query returns different matches for different projects.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / project_id / description
      Previous value: -"Project ID from list_projects"New value: +"UUID as returned by list_projects - not the project name, title, or slug, and not guessable. Fetch it once and reuse the same id across tools. An id outside the caller's organization returns \"Project not found or access denied\" rather than empty data, and a project withheld by a plan limit returns a plan error that retrying cannot clear. It bounds the search to the packages assigned to this project, so the same query returns different matches for different projects."
  2. Changed1 schema field changed
    • addedInput schema / properties / query / description
      Added value: +"Free-text description of the need - a use case, behavior, or purpose, e.g. \"date range picker\". Not a component name and not a glob."
  3. First observed

TDQS

A5/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, the description reveals substantive behavioral traits: semantic ranking requires AI features on Team plan or above and falls back to name/import-path matching with a null score, no close match returns an empty list rather than an error, and null scores/no results do not imply the component is missing. It also documents how project_id scoping affects results and error behavior. This is far more than the annotation alone conveys.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Despite being long, the description is tightly packed: main behavior first, then usage conditions, query semantics, exclusions, plan-dependent behavior, and failure semantics. Each sentence earns its place and covers an edge case an agent would otherwise discover only at runtime. The structure front-loads the core purpose and routes away from sibling tools early.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a semantic search tool with conditional ranking behavior, no output schema, and two required parameters, the description covers the invocation, the expected result shape (up to 10 ranked matches with relevance score), plan fallback, empty-result semantics, and recovery strategies. Nothing essential to calling the tool correctly is missing.

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

Parameters5/5

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

Although schema coverage is 100%, the description adds meaning beyond the schema: it clarifies that the query is a free-text need, not a component name/glob/props expression, and gives concrete examples. For project_id, it emphasizes that the value is a non-guessable UUID from list_projects, not the project name, and explains plan-error and access-denied behavior. This materially helps an agent supply correct parameters.

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?

The description opens with a precise verb and resource: it searches components across every package assigned to the project, by use case/behavior/description, and returns up to 10 ranked matches with a relevance score. It also explicitly differentiates itself from siblings: get_component for exact-name lookup and list_components for the full catalog. An agent can identify what this tool is for without opening the 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?

The description states exactly when to use the tool ('when you can describe what the UI must do but do not know the component name') and when not to use it (exact name known → get_component; full catalog wanted → list_components). It also gives practical retry guidance for cases where semantic matching yields no results. This is explicit, actionable routing guidance.

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.