Skip to main content
Glama

Search AI Canvas icons

search_icons
Read-onlyIdempotent

Search the AI Canvas icon set by keyword to find icons matching names, tags, or categories for UI needs and user requests; then install the chosen name and style.

Instructions

Keyword search across the AI Canvas icon set (React icons, four styles each: Line is free with an account; Duotone, Solid and Solid duotone are Premium). Matches on name, tags and category, best match first. Use when the user needs an icon ("a trash icon", "something for settings") or when building UI that needs icons. Then call get_icon_install with the chosen name and style.

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": {
      "query": "<query>"
    },
    "name": "search_icons"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax number of matches to return. Default 20.
queryYesWhat the icon shows or is for, e.g. "delete", "arrow right", "ai agent".
categoryNoOnly icons in this category slug, e.g. "arrows", "ai-dev", "interface". Every result carries its category.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.2

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the read-only/idempotent annotations, the description discloses the four style variants and the licensing split (Line free with an account, Duotone/Solid/Solid duotone Premium) and states that results are ranked best match first. That licensing detail is decision-relevant information an agent would not get from the annotations alone.

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?

Three sentences, each carrying distinct load: what is searched and how, the licensing constraint, when to use it, and the follow-up call. Nothing is repeated and the core capability is front-loaded.

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 does enough by implying results carry a name and style and are relevance-ordered. It could be tighter on whether premium styles are flagged in results, which matters given the licensing note, but it is largely sufficient for a three-parameter search tool.

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 coverage is 100%, so the baseline is 3, but the description adds meaning by explaining that `query` is matched against name, tags and category rather than just a free-text label. The `limit` and `category` parameters are left entirely to the schema.

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 states a specific verb and resource ('Keyword search across the AI Canvas icon set') and pins down matching scope (name, tags, category) plus result ordering. An agent can immediately distinguish it from search_components, which targets components rather than icons.

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?

It gives explicit trigger conditions ('when the user needs an icon', 'when building UI that needs icons') and routes the agent onward to get_icon_install with the chosen name and style. It stops short of any when-not-to-use guidance or a direct contrast against search_components.

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