Given an icon id (from search_icons), return related/similar Infyicon icons — same theme in the same and other styles. Great for offering variations or building a matching icon set.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Icon id like hammer-16_66091 | |
| limit | No | Max results (default 12) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses that the operation returns related icons rather than mutating anything, and it explains the relationship criterion ('same theme in the same and other styles'). It doesn't detail ordering or matching algorithm, but those are not essential for selection and invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences deliver the purpose, input provenance, output behavior, and use cases with no filler. The core function is front-loaded and the usage tip is brief but valuable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only tool with two well-documented parameters and no output schema, the description provides everything needed: what to pass in, what comes back, and why you'd use it. Nothing important is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already documents both parameters at 100% coverage. The description adds meaningful cross-tool context by specifying that the id comes from search_icons, which helps the agent supply a valid value without additional lookup.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific action (return related/similar icons), a concrete resource (Infyicon icons), and the relationship (same theme in same and other styles). It also ties the input to search_icons, distinguishing this from direct asset fetch tools like get_icon_svg or get_icon_png.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It clearly states that the input is an icon id from search_icons and gives use cases ('offering variations or building a matching icon set'). It doesn't explicitly list exclusions or direct alternative conditions, but the sibling names and 'related/similar' framing make the intended context easy to infer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clear, distinct roles: search, list categories, and fetch SVG/PNG by id. Some overlap exists because search_icons already returns SVG and PNG URLs, but get_icon_svg/get_icon_png are clearly meant for direct retrieval by known id.
The naming pattern is generally consistent using verb_noun style: get_icon_svg, get_icon_png, list_categories, search_icons. uicons_lookup deviates slightly by starting with a product name instead of a verb, but it is still understandable and similar in spirit.
Five tools is a well-scoped size for an icon service: search, browse categories, retrieve two format types, and check webfont usage. Each tool has a clear purpose and none feel redundant enough to remove.
The core icon workflow is covered: search, category discovery, SVG/PNG retrieval, and UI-font lookup. Minor gaps exist around category-specific icon listing or richer metadata, but agents can successfully search and fetch icons end-to-end.