Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

oldnavy_product

Fetch product details for an Old Navy, Gap, Banana Republic, or Athleta item using a color-specific product id and brand code, returning images, rating, description, and priced size offers.

Instructions

Get an Old Navy, Gap, Banana Republic, or Athleta product. Returns product-detail data for one color variant: name, description, images, aggregate rating, and every size offered in that color as a separate priced offer. pid is a color-specific product id, as returned by oldnavy-search's product colors[].id field (not the bare base product id). Select the storefront with the brand parameter (on for Old Navy, gap for Gap, br for Banana Republic, at for Athleta; defaults to on) -- it must match the brand the pid was found under.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pidYesColor-specific product id, from a search result's colors[].id field
brandNoStorefront the pid belongs to

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.17.5
    • addedInput schema / properties / brand / enum
      Added value: +[
+  "on",
+  "gap",
+  "br",
+  "at"
+]
  2. Addedv1.14.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it does well by disclosing the return shape (name, description, images, aggregate rating, and each size as a separate priced offer) even without an output schema. It omits auth requirements or rate limits, but the operational 'brand must match pid' constraint is a meaningful behavioral disclosure.

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

Conciseness5/5

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

Front-loaded with the core action, then the return shape, then the id provenance, then the brand mapping. Three dense sentences with no filler; each clause carries actionable information.

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

Completeness4/5

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

For a two-param detail tool with no output schema and no annotations, the description covers returns, id provenance, and the brand-matching constraint well. It lacks auth/permission or failure-mode notes, leaving a minor gap against the burden it must carry.

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 already 100%, so baseline is 3, but the description adds real value: it maps brand codes (on/gap/br/at) to storefronts, states the default ('on'), and stresses the pid must be color-specific and brand-matched. That goes beyond the terse schema descriptions.

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?

States a specific verb (Get) and resource (product) across four named brands, and clearly distinguishes itself from oldnavy_search by noting the pid is a color-specific id sourced from search results. An agent can tell what it returns (single color-variant detail) versus what the search/category siblings return.

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?

Explains the prerequisite workflow: the pid must come from oldnavy-search's product colors[].id field, not the bare base id, and brand must match the brand the pid was found under. This is clear contextual guidance, though it stops short of explicitly stating when not to use it or naming alternative detail tools.

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

Deploy Server

Other Tools