UCP 2026-04-08 catalog search. Free-text query over the catalog; returns UCP product objects in structuredContent. Call with no query to list everything.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Free text, e.g. "waterproof jacket". Omit to return the whole catalog. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It usefully discloses the return shape and the no-query listing behavior, but it does not mention pagination, result limits, read-only guarantees, or any operational constraints.
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 short sentences with zero filler. The primary behavior is front-loaded, and the no-query default is communicated in a compact, memorable way.
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 one optional parameter and no output schema, the description covers the core invocation behavior, return type, and default listing behavior. It is slightly incomplete in omitting operational details like pagination or limits, but it is adequate for basic 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?
The input schema already documents the single parameter completely, including free-text guidance and the omit-to-list behavior. The description mostly restates what the schema says, so it adds only marginal semantic value beyond the structured definition.
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 clearly identifies the tool as a free-text catalog search and states that it returns UCP product objects in structuredContent. It is specific enough to be distinguished from sibling tools like lookup_catalog and list_products, though it does not explicitly name those alternatives.
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 a concrete usage pattern: call with a free-text query, or omit the query to list everything. However, it does not explicitly explain when to choose search_catalog over lookup_catalog or list_products, leaving sibling differentiation mostly to inference.
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.
check_stock and report_problem are clearly distinct, but four product-retrieval tools overlap: get_product, lookup_catalog, search_catalog, and list_products all return product data in similar forms, and search_catalog with no query duplicates list_products. Their descriptions help somewhat, but an agent could reasonably misselect between get_product and lookup_catalog or between list_products and search_catalog.
All six tools use a consistent verb_noun snake_case pattern: check_stock, get_product, list_products, lookup_catalog, report_problem, and search_catalog. There are no mixed conventions or irregular verbs.
Six tools is a reasonable size for a catalog and stock server. The count is neither bloated nor too thin, and each tool has a clear operational role even where retrieval boundaries are fuzzy.
The read-only catalog surface is well covered: search, identifier lookup, single-product details, full listing, and live stock/price are all present. The report_problem tool also covers the main dead-end failure mode for an agent, so there are no obvious missing reads.