Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

nike_search

Search Nike products by keyword or browse categories to get normalized product groups with pricing, colorways, purchasable variants, and filter navigation.

Instructions

Search or browse Nike products. Searches Nike.com product listings by keyword, or browses a category/subcategory listing by slug, with real pagination. Exactly one of keyword or category is required. Returns normalized product groups with pricing, colorway images, and every purchasable color variant, plus filter and subcategory navigation data (facet_nav) already present on the same response -- both keyword search and a category listing's first page include filter groups (Gender, Color, Price, Size, and similar); only a category listing includes a breadcrumb trail and subcategory drill-down options, and only its first page (a category listing's later pages do not repeat navigation data). Keyword search is best-effort relevance, not a guaranteed keyword match: for an obscure or nonsense keyword, Nike's own search index falls back to its own recommended results instead of returning an empty list, and there is currently no reliable signal in the response to distinguish a true keyword match from that fallback behavior. A keyword Nike's own search router treats as structurally empty (for example a punctuation-only query) does return a genuine empty result. Category values come from nike-categories' own slug field, or from a prior response's own facet_nav navigation paths (with the leading /w/ stripped). Requesting a page beyond the available result pages returns a not-found error.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoOne-based page number, defaults to 1
keywordNoSearch keyword. Exactly one of keyword or category is required.
categoryNoCategory/subcategory browse slug, from nike-categories' own slug field or a prior response's facet_nav navigation. Exactly one of keyword or category is required.
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure — and it does so thoroughly: keyword search is best-effort relevance with Nike's fallback to recommended results and no reliable signal to distinguish that fallback; only a structurally empty keyword yields a genuine empty result; navigation data appears only on the first page of a category listing; and paging beyond results returns a not-found error. These are exactly the hidden quirks an agent cannot infer from schema alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a dense block of roughly 200 words with no filler. Every sentence carries a distinct operational claim: return shape, dual-mode constraint, navigation data asymmetry, fallback semantics, and error cases. The structure is reasonable — purpose and the central constraint are front-loaded — and feels slightly long, which is justified by the dual-mode complexity and the edge-case-heavy behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description is the sole source of contextual risk knowledge, and it is complete: normalized product groups with pricing and variants, facet_nav and breadcrumb presence per mode, filter groups, keyword fallback and empty-result semantics, category value provenance, and pagination errors. An agent has everything necessary to select the right mode and interpret unexpected outcomes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for all three parameters, so the baseline is 3. The description adds real value beyond the schema: the category sourcing rule (strip leading /w/), the page beyond range behavior, and the notion that a searched keyword must not be structurally empty to get a meaningful verdict all attach to parameters and are not expressed in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Starts with a specific verb and resource: 'Search or browse Nike products. Searches Nike.com product listings by keyword, or browses a category/subcategory listing by slug'. It names the two distinct modes of the tool and its target resource (Nike.com product listings), which makes it clearly distinguishable from the dozens of sibling search and product tools in the catalog.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance on how to invoke each mode: 'Exactly one of keyword or category is required', plus concrete instructions on sourcing category values from nike-categories slug fields or from a prior facet_nav path with the leading /w/ stripped. The only gap is that it does not explicitly state when NOT to use this tool, e.g., that nike_product should be used for a single product page.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Crawlora-org/crawlora-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server