search_itemsSearch 1stDibs with the given query and optional page number and filters. Filters are in the format of a query string like category=furniture&location=usa-north-america. Read the taxonomy to discover categories, facets and filters.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Jump to a specific page number | |
| query | Yes | Search Query | |
| filters | No | Filters to apply to the search |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It discloses the filter format and the need to read the taxonomy, which is useful behavioral context. However, it does not mention response format, pagination behavior, rate limits, or any side effects, leaving some aspects unstated.
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?
Three concise sentences, front-loaded with the core purpose. Each sentence serves a purpose: stating the action, explaining filter syntax, and directing the user to taxonomy. No unnecessary words.
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 three parameters, the description covers the essential inputs, filter format, and a pointer to taxonomy for valid filter values. It lacks an explicit response structure, but this is not strictly required for correct invocation, so it is largely complete.
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 have schema descriptions, meeting the baseline. The description adds significant value by specifying the 'filters' parameter's exact query-string format with a concrete example (category=furniture&location=usa-north-america), which goes beyond the generic schema description.
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 states the tool's function: 'Search 1stDibs with the given query and optional page number and filters.' It uses a specific verb ('search'), names the resource ('1stDibs items'), and differentiates from siblings like browse_items and item_details by emphasizing query-based search with filters.
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 usage through 'Search 1stDibs with the given query' and advises 'Read the taxonomy to discover categories, facets and filters,' suggesting a workflow. However, it does not explicitly state when to choose search over browse_items or item_details, nor does it provide exclusion conditions or alternatives.
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.
browse_items and search_items both return item lists, but browse is clearly category-driven while search is query-driven. item_details and read_taxonomy are distinct. The descriptions help differentiate the two listing tools.
Most tools follow a verb_noun pattern (browse_items, read_taxonomy, search_items), but item_details breaks it by using noun_noun. The inconsistency is minor and does not impede readability.
Four tools cover the core discovery workflow: taxonomy, browse, search, and item details. This is a well-scoped set for a marketplace listing server, with no redundancy or excessive surface.
The set covers the main actions needed to explore and retrieve item information. A minor gap is that read_taxonomy requires a category, so you cannot list all root categories without prior knowledge, but the description provides top-level categories.