check_shopCheck a store like a shopping agent: anti-bot wall, robots.txt for agents, UCP, product data, price/stock truth. Read-only, never buys. Cached 1 h. Example: {"domain":"example-store.com"}
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Store domain or URL | |
| customer_request | No | Optional: what your user wants (use, budget, deadline) |
Changes observed during successful MCP inspections.
Input schema / properties / customer_request / descriptionPrevious value: -"Optional: what your user wants in plain words (use, budget, deadline), e.g. vacuum for thick carpet under 300 EUR before Friday. Faceabot then checks the store's matching products against it (use, stock, delivery, returns, budget)."New value: +"Optional: what your user wants (use, budget, deadline)"Input schema / properties / domain / descriptionPrevious value: -"Store domain or URL, e.g. example-store.com"New value: +"Store domain or URL"Input schema / properties / customer_requestAdded value: +{
+ "description": "Optional: what your user wants in plain words (use, budget, deadline), e.g. vacuum for thick carpet under 300 EUR before Friday. Faceabot then checks the store's matching products against it (use, stock, delivery, returns, budget).",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description says 'Read-only, never buys', but annotations set readOnlyHint to false. This directly contradicts the safety profile an agent would infer from the annotations. Although 'Cached 1 h' adds useful behavioral context, the read-only contradiction is serious.
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 compact and front-loaded: it states the core check, lists what is inspected, notes the read-only/cache behavior, and gives a concrete example. Every sentence earns its place.
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?
The description gives a useful sense of what the tool inspects and includes caching context, but there is no output schema and no explanation of what the check returns. It also fails to reconcile the read-only claim with the annotations.
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 both parameters are documented in the schema. The description adds an example for domain but does not explain customer_request or add meaning beyond the schema. Baseline 3 is appropriate when the schema already carries parameter semantics.
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 a specific verb and resource: checking a store, with enumerated aspects such as anti-bot wall, robots.txt, UCP, product data, and price/stock truth. It distinguishes check_shop from find_shop reasonably well through the verb 'check' and the inspection-focused scope, though it does not explicitly name siblings.
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?
Usage is implied as pre-purchase or shopping-agent verification, reinforced by 'like a shopping agent' and 'never buys'. However, there is no explicit when-to-use or when-not-to-use guidance, nor any direct alternative named among the many sibling tools.
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.