Profile Ecommerce Platform

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

The description layers substantial behavioral context beyond the readOnly/openWorld/idempotent annotations: no browser execution, static-read-only methodology, confidence tied to evidence kind (vendor header high, HTML substring low), the not_extractable fallback instead of guessing, and the requirement for an APIFY_TOKEN with per-call credit consumption. It is fully consistent with annotations — 'Read only' matches readOnlyHint=true, and the safety guarantees ('never adds an item, never starts a checkout, never submits anything') reinforce the non-destructive profile.

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?

Five sentences, each earning its place: scope, output format, method/limitation, confidence model, and auth/cost. Core purpose is front-loaded in the first clause, and there is zero filler or restatement of the title.

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 7-parameter tool with no output schema and no siblings, the description covers everything an agent needs to select and invoke it correctly: the detected attributes stand in for output fields, the flat-row return shape is stated, failure behavior (not_extractable) is disclosed, and operational requirements (credits, token, cost) are explicit. The rich input schema carries parameter semantics, leaving no material gap.

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 baseline is 3 and the schema does the heavy lifting. The parameter descriptions are exceptionally rich on their own (caching semantics, why checkCheckout exists, residential-exit retry behavior), and the main description wisely does not repeat them. It adds only peripheral context like the APIFY_TOKEN credential requirement; no compensation for missing parameter documentation is needed.

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 opens with a specific verb and resource — 'Detect which ecommerce platform a storefront runs on' — and enumerates the full target set (Shopify, WooCommerce, Magento, etc.) plus the secondary data points (payment providers, catalogue size, currencies, shipping destinations). It also states the output shape ('one flat Clay ready row'), leaving no ambiguity about what the tool produces.

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?

With no sibling tools to differentiate against, the description instead sets clear applicability boundaries: it is a static homepage/sitemap read, and a storefront that only reveals its platform after JavaScript runs is reported as not_extractable rather than guessed. This implicitly tells an agent when the tool is the right choice and when results will be inconclusive, though it stops short of explicit when-to-use/when-not-to-use phrasing or named alternatives.

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