find_replacementFind and rank Digche replacements for an icon from Lucide, Heroicons, Material Symbols, Font Awesome, or another library. Include the UI context for a more useful match.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 1 to 10 candidates. | |
| context | No | Functional UI context, for example Back button in mobile navigation. | |
| sourceIcon | Yes | Original component or icon name, for example ArrowLeft. | |
| sourceLibrary | No | ||
| preferredStyle | No | Linear |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / limit / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "string"
+ }
+]Input schema / properties / limit / defaultRemoved value: -5Input schema / properties / limit / descriptionAdded value: +"1 to 10 candidates."Input schema / properties / limit / maximumRemoved value: -10Input schema / properties / limit / minimumRemoved value: -1Input schema / properties / limit / typeRemoved value: -"integer"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must carry the full burden of behavioral disclosure. It states the purpose (find and rank) but does not mention whether the operation is read-only, how results are ranked, or any side effects—though the tone implies a read-only action.
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 sentences, front-loaded with the main action, and no wasted words. The description is concise and immediately communicates the core purpose.
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?
The tool has 5 parameters and no output schema or annotations. The description tells what the tool does but not what a 'replacement' consists of, how ranking works, or the structure of the returned candidates. It is adequate for a simple tool but leaves gaps.
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?
Schema coverage is roughly 60% (sourceLibrary lacks a description). The description adds meaning to the context parameter ('Include the UI context for a more useful match') and clarifies that sourceLibrary is optional ('or another library'), but it doesn't significantly elaborate on other parameters.
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 uses specific verbs 'Find and rank' and identifies the resource 'Digche replacements', along with supported libraries (Lucide, Heroicons, Material Symbols, Font Awesome, or another). This clearly distinguishes the tool from broader search/recommendation siblings.
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?
The description provides a practical tip about including UI context but gives no guidance on when to choose this tool over siblings like search_icons or recommend_icons. There are no exclusions or alternative scenarios, leaving the decision to the agent.
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.
Each tool targets a distinct workflow stage—discovery, replacement, bulk recommendation, comparison, and retrieval—so an agent can usually choose correctly. The only slight ambiguity is preview_icons, whose search-and-preview mode overlaps with search_icons' built-in preview image.
All six tools use a consistent snake_case verb_noun convention (find_, get_, list_, preview_, recommend_, search_), each verb uniquely identifies the action. No mixed patterns or vague generic names are present.
Six tools is well-scoped for an icon library: it covers discovery, selection, retrieval, and migration without bloat. Every tool has a clear role and the set is neither thin nor overwhelming.
The set covers the full icon workflow: discover via search/categories, evaluate via preview/recommend, retrieve via get_icon_svg, and migrate via find_replacement. A minor gap is the lack of batch SVG retrieval or detailed per-icon metadata, but agents can work around it by looping get_icon_svg.