Search the InfySVG catalog of free SVG cut files by keyword. Returns matching designs with their page URLs. Send the user to the page for downloads — every page offers free SVG, PNG, DXF and PDF plus recolouring, no account needed.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results, default 10, max 30 | |
| query | Yes | What to search for, e.g. "crown", "halloween skull" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses that the tool returns page URLs rather than direct files, and adds that downloads need no account and include multiple formats plus recolouring. Ordering, pagination, and error behavior are not covered, but the most decision-relevant behavior is present.
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?
The description is two focused sentences with the core action front-loaded. Every clause earns its place, including the downstream instruction to send users to the page for downloads.
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 search tool with two parameters and no output schema, the description provides purpose, return shape, and a clear follow-up action. It omits details like result ordering or empty-result behavior, but those are not necessary for correct invocation.
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 100%, with both query and limit already well described in the input schema. The description adds no additional parameter-level meaning, so the baseline score of 3 applies.
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 verb and resource ('Search the InfySVG catalog') and states the outcome (matching designs with page URLs). It does not explicitly contrast itself with sibling tools like get_design or list_categories, but the search intent is clearly distinct.
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 implies the tool is for keyword-based catalog searches and tells the agent to send the user to result pages for downloads. However, it does not state when to prefer this over get_design or list_categories, nor does it provide explicit exclusions.
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 addresses a clearly distinct concern: fetching a specific design, retrieving license terms, listing categories, and searching designs. There is no meaningful overlap between get_design and search_designs because one is targeted lookup by slug and the other is keyword discovery.
All tool names follow a consistent lowercase snake_case verb_noun pattern: get_design, get_licence, list_categories, search_designs. The different verbs reflect different actions while remaining predictable and readable.
Four tools is a well-scoped size for a clipart catalog server focused on discovery, retrieval, licensing, and browsing. Each tool earns its place and the total feels neither thin nor bloated.
The core user journey—searching, viewing design details, checking license terms, and exploring categories—is well covered. A minor gap is the lack of an explicit tool to list all designs within a category, though search and category page URLs partially compensate.
