get_iconReturn one icon by ID. Metadata is public; raw SVG requires a Pro API token with icons:read and mcp:use scopes.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The catalog icon ID, as shown in search results and icon page URLs. | |
| format | No | svg is an alias for includeSvg=true; metadata (default) returns metadata only. | |
| includeSvg | No | Include the raw body and wrapped SVG markup. Requires a Pro token with icons:read. Default false. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With readOnlyHint already declared, the description adds meaningful context: metadata is public, SVG requires Pro token with specific scopes (icons:read and mcp:use). This warns the agent about potential auth failures, going beyond the annotation.
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: first states core function, second adds critical access constraint. Minimal waste, well-structured.
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 single-icon retrieval tool with one required parameter, the description covers the essential behavioral caveat (SVG access restriction) and the schema fully documents parameters. The absence of an output schema is mitigated by the simple return type, so completeness is high.
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?
All three parameters (id, format, includeSvg) are fully described in the schema with types, defaults, and the alias relationship. The description adds no additional parameter semantics beyond what's in the schema, so baseline 3 is appropriate.
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 'Return' with the resource 'one icon by ID,' clearly distinguishing from sibling tools like get_icon_collection and search_icons. It precisely states the tool's core function.
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 gives clear context: use this tool when you have an icon ID and need its metadata or SVG. It notes the auth prerequisite for SVG but does not explicitly mention alternative tools for discovery, relying on the ID-based scope.
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 clearly distinct purposes (search, get, create, add/remove, export). However, `recommend_icons_for_ui` and `generate_icon_kit_for_project` overlap semantically with `search_icons` and `create_icon_kit`, which could cause confusion despite good descriptions.
All tool names follow a consistent verb_noun pattern, using snake_case throughout. The optional prepositional phrases (e.g., `add_icon_to_collection`, `remove_icon_from_collection`) are consistent and predictable.
12 tools is well-scoped for an icon search and collection management server. Each tool covers a distinct operation without unnecessary bloat, fitting comfortably in the ideal 3-15 range.
The set covers search, retrieval, creation, listing, adding/removing icons, and export. Missing operations include deleting a collection and updating collection metadata, which are notable gaps in lifecycle management but can be worked around.