Store Canary

Check a store's policy pages

check_policies

Read-onlyIdempotent

Check that the homepage links to privacy, terms, shipping and returns/refunds pages, and that each linked page on the same site loads. Read-only: one run of GET requests only; never logs in, adds to cart or submits forms. Nothing is monitored or saved; ongoing checks are Store Canary Pro. A bare hostname is fine; URL paths are ignored and the host's homepage is checked.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "check_policies"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	The store's public address, for example https://example.com. A bare hostname (example.com) is fine. Any path, query or fragment is ignored: the homepage of the host is checked.

Output Schema

Name	Required	Description
`url`	Yes	Normalized store origin that was checked.
`status`	Yes	checked = findings below; otherwise no store request was made.
`liteUrl`	Yes	Store Canary Lite on WordPress.org (free).
`overall`	Yes
`summary`	Yes
`auditUrl`	Yes	Full Store Canary audit (plain external link).
`findings`	Yes
`checkedAt`	Yes
`reportUrl`	No	Shareable read-only report page. The result is encoded in the link; nothing is stored.
`proTrialUrl`	Yes	Store Canary Pro 30-day free trial.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026

changedInput schema / properties / url / description

Previous value: -"The store's public address, for example https://example.com"New value: +"The store's public address, for example https://example.com. A bare hostname (example.com) is fine. Any path, query or fragment is ignored: the homepage of the host is checked."

Changed1 schema field changedOct 30, 2026

addedOutput schema / properties / reportUrl

Added value: +{
+  "description": "Shareable read-only report page. The result is encoded in the link; nothing is stored.",
+  "format": "uri",
+  "type": "string"
+}

AddedOct 30, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Adds real behavior beyond the annotations: only GET requests, no login, no add-to-cart, no form submission, and nothing is monitored or persisted. That materially expands on readOnlyHint=true and destructiveHint=false. It stops short of covering pacing/rate behavior or failure-mode handling, keeping it at a 4 rather than a 5.

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?

Four sentences, each carrying distinct information: what is checked, the request safety profile, the persistence/monitoring boundary, and URL normalization. Nothing redundant, and the core check is front-loaded.

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 single-parameter check tool with a rich annotation set and an output schema, the description supplies what the structured fields cannot: request methodology and non-persistence. Return-value detail is legitimately delegated to the output schema; only edge-case behavior (e.g., when no policy link is found) is left unstated.

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

Parameters3/5

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

Schema coverage is 100% and the schema property already documents the bare-hostname and ignored-path behavior, so the description is largely echoing structured data. The restatement usefully emphasizes that the host's homepage is the real target, but adds no new syntax or constraint. Baseline 3 applies when the schema does the heavy lifting.

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 and resource ('check that the homepage links to privacy, terms, shipping and returns/refunds pages, and that each linked page on the same site loads'), which is concrete enough to separate it from siblings like check_seo_basics, check_exposure and check_ssl. The scope of the check (link presence + page load) is fully enumerated.

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?

Clear usage context: one-off, read-only GET run, with the explicit routing signal that continuous monitoring belongs to 'Store Canary Pro'. It does not name sibling checks as alternatives, so it falls short of explicit when-not-to-use guidance, but the one-shot framing is unambiguous.

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

All Store Canary tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.