Browse the SvGrid demo catalogue: id, title, category and a one-line blurb. Call with no arguments for the category index, then filter with query or category, then read one with get_example_source.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results, default 25, max 100. | |
| query | No | Free-text filter over id, title, blurb and category. | |
| category | No | Exact category, e.g. "Kanban". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden. It explains the no-arguments behavior, the filtering behavior, and the returned fields. It does not mention ordering, case sensitivity, or pagination beyond the schema's limit default, but the high-level behavior is well disclosed for a simple browsing tool.
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 with no filler. The resource and fields are front-loaded, followed by a compact workflow. Every clause earns its place.
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 description covers the full lifecycle from index browsing to filtering to reading a detail page, names the returned fields, and points to the relevant sibling tool. For a simple read-oriented tool with no output schema, this is complete enough for an agent to call it correctly.
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 description coverage is 100%, so the parameters are already well documented. The description reinforces that query and category are filters, but adds little semantic detail beyond the schema. 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 a specific verb ('Browse') with a clear resource ('SvGrid demo catalogue') and lists the exact fields returned. It also names the follow-up sibling tool (get_example_source), distinguishing the listing/browsing function from reading a single example.
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 explicit usage guidance: call with no arguments for the category index, then filter by query or category, then read one example with get_example_source. It does not explicitly contrast with the 'search' sibling, but the intended workflow is clear enough for correct selection.
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.
The search→fetch and list_examples→get_example_source pairs form clear workflows, and check_svgrid_code is distinct. The only real ambiguity is that fetch also accepts a demo id, which overlaps somewhat with get_example_source, though fetch returns page text rather than .svelte source.
Most tools follow a descriptive verb_noun pattern: get_api_reference, get_example_source, list_examples, check_svgrid_code. The bare verbs search and fetch are minor deviations, but the names remain predictable and easy to distinguish.
Six tools is a tight, well-scoped set for a documentation-and-code-support server. Each tool earns its place and together they cover discover, read, reference, example, and verify workflows without redundancy.
The tool surface covers the full assistant loop: search documentation, fetch doc content, read the API reference, browse and copy demo source, and validate code against the real SvGrid API. There is no obvious missing operation that would create a dead end for an agent.