preview_iconsRender candidate Digche icons as a single image so a person can compare them before choosing. Pass slugs from an earlier tool call, or a query to search and preview in one step.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 1 to 24 icons. | |
| query | No | Used only when slugs are not supplied. | |
| slugs | No | Slugs from a previous result. | |
| style | No | Linear | |
| theme | No | light |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It states that the tool renders a single image for comparison, but it does not mention read-only nature, output format details, or how conflicting inputs (slugs + query) are handled. Some behavior is implied (e.g., search+preview) but not fully elaborated.
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 compact sentences, front-loaded with purpose and then usage. Every word contributes, with no redundant restating of the tool name or schema details.
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 tool with 5 optional params and no output schema, the description covers core behavior and both usage modes. It omits some details like default handling when neither slugs nor query are supplied, and it doesn't explicitly describe the returned image format, but the schema fills some gaps (defaults, limits).
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 covers 60% of parameters (limit, query, slugs), and the description adds relational meaning: slugs come from a previous tool call, query is an alternative for one-step search+preview. However, style and theme have no description and are left only as enum labels, relying on implicit understanding.
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 the specific verb 'Render' with a clear resource ('candidate Digche icons') and the intended outcome ('compare them before choosing'). It distinguishes the tool from siblings like search_icons (which searches/returns metadata) and get_icon_svg (which returns a single SVG) by emphasizing a single composite image for comparison.
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 explicitly defines two usage modes: pass slugs from an earlier tool call, or use a query to search and preview in one step. This clearly indicates when to use the tool, though it does not name alternative tools or state exclusions (e.g., not for fetching SVGs).
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 has a clear, distinct purpose: searching, retrieving, listing, previewing, recommending, and finding replacements. Even though search_icons and preview_icons both accept queries, their intents (discovery vs. comparison) are clearly differentiated in the descriptions.
All tool names follow a consistent verb_noun pattern in snake_case (find_replacement, get_icon_svg, list_categories, preview_icons, recommend_icons, search_icons), making the API predictable and easy to navigate.
With 6 tools, the set is well-scoped for an icon library server. Each tool serves a essential step in the icon selection workflow without redundancy or bloat.
The tool surface covers the full lifecycle: discovering categories, searching, previewing, retrieving SVGs, recommending sets, and replacing third-party icons. The only minor gap is the absence of a direct metadata-only lookup, but search summaries and SVGs largely fill this need.