ReturnCheck

check_return

ReturnCheck verifies which return policy actually applies to this purchase. BEST RESULTS: send the product page you already have as page_text (or page_html) along with product_url — your browser renders JavaScript and is not blocked by retailers, so this works on any store and is faster. Without it we fetch the page ourselves and reach the policy for about 1 in 3 US retailers (17 of 50 measured 2026-08-28; mostly Shopify and direct-to-consumer brands — large retailers and marketplaces block server-side reads). You get a verified verdict — YES / YES_WITH_CONDITIONS / NO / UNKNOWN — with the exact policy clause quoted verbatim, source URL, return window/deadline, fees and a confidence score. Never invents: returns UNKNOWN instead of guessing, and UNKNOWN is free.

Input Schema

Name	Required	Description
`reason`	No
`merchant`	No
`page_html`	No	RECOMMENDED (alternative to page_text). Raw HTML of the same page. Slightly better than page_text: we can also read structured data (JSON-LD) from it.
`page_text`	No	RECOMMENDED. Plain text of the product or returns page you already have open. We verify against this instead of fetching: works on any store, no blocking, no JavaScript problem, and faster. Still never invents: no verifiable clause -> UNKNOWN (free).
`product_url`	Yes	The product page URL (http/https).
`seller_name`	No
`buyer_country`	Yes	ISO 3166-1 alpha-2, e.g. 'US'.
`delivery_date`	No	YYYY-MM-DD (optional; preferred for the deadline).
`purchase_date`	No	YYYY-MM-DD (optional).
`item_condition`	No
`page_source_url`	No	URL of the supplied page_text/page_html when different from product_url. Caller-declared provenance; not independently fetched.
`payment_signature`	No	OPTIONAL. x402 payment authorization, base64 — the same envelope the PAYMENT-SIGNATURE header carries over HTTP. Use it to pay per call with no account and no signup. How: call once without it; if the free trial is exhausted you get the payment terms in structuredContent (x402Version, accepts[]); sign that authorization and call again with payment_signature set. Terms are also published at /.well-known/x402. UNKNOWN verdicts are never settled: the authorization simply expires unused.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 2, 2026

addedInput schema / properties / page_source_url

Added value: +{
+  "description": "URL of the supplied page_text/page_html when different from product_url. Caller-declared provenance; not independently fetched.",
+  "type": "string"
+}

Changed1 schema field changedAug 31, 2026

addedInput schema / properties / payment_signature

Added value: +{
+  "description": "OPTIONAL. x402 payment authorization, base64 — the same envelope the PAYMENT-SIGNATURE header carries over HTTP. Use it to pay per call with no account and no signup. How: call once without it; if the free trial is exhausted you get the payment terms in structuredContent (x402Version, accepts[]); sign that authorization and call again with payment_signature set. Terms are also published at /.well-known/x402. UNKNOWN verdicts are never settled: the authorization simply expires unused.",
+  "type": "string"
+}

Changed2 schema fields changedAug 28, 2026

changedInput schema / properties / page_html / description

Previous value: -"Optional: raw HTML of the page you already have. If provided, ReturnCheck verifies against it instead of fetching — best coverage, bypasses sites that block server-side reads. Still never invents: no verifiable clause -> UNKNOWN."New value: +"RECOMMENDED (alternative to page_text). Raw HTML of the same page. Slightly better than page_text: we can also read structured data (JSON-LD) from it."

changedInput schema / properties / page_text / description

Previous value: -"Optional: plain text of the page (alternative to page_html)."New value: +"RECOMMENDED. Plain text of the product or returns page you already have open. We verify against this instead of fetching: works on any store, no blocking, no JavaScript problem, and faster. Still never invents: no verifiable clause -> UNKNOWN (free)."

Changed2 schema fields changedAug 23, 2026

addedInput schema / properties / page_html

Added value: +{
+  "description": "Optional: raw HTML of the page you already have. If provided, ReturnCheck verifies against it instead of fetching — best coverage, bypasses sites that block server-side reads. Still never invents: no verifiable clause -> UNKNOWN.",
+  "type": "string"
+}

addedInput schema / properties / page_text

Added value: +{
+  "description": "Optional: plain text of the page (alternative to page_html).",
+  "type": "string"
+}

First observedAug 23, 2026

TDQS

A4.4/5.0

Behavior4/5

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

No annotations exist, so the description carries the full burden, and it does most of it: it discloses the never-invents guarantee (UNKNOWN instead of guessing), that UNKNOWN is free, the 17-of-50 measured success rate, and the payment flow with expiry semantics. It is somewhat silent on latency/timeout behavior and on how confidence scores are derived, which a caller would want for a scraping-dependent tool.

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?

Front-loaded on the best-result path and free on the important constraint, and every sentence carries information. It is dense and somewhat repetitive — the page_text recommendation and the 'never invents / UNKNOWN is free' point appear more than once — which costs it a point.

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?

There is no output schema, so the description must describe the return shape, and it does: verdict enum (YES / YES_WITH_CONDITIONS / NO / UNKNOWN), quoted clause, source URL, return window/deadline, fees, and confidence score. Together with the payment-etiquette detail, an agent has everything needed to call and interpret it.

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 description coverage is 67% and the schema already documents the key params (page_text, page_html, payment_signature, dates, country). The description's page_text/page_html guidance largely restates what those schema descriptions say, adding the rationale but little new semantics; unenumerated params like merchant, seller_name, reason, and item_condition are explained nowhere.

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 — 'verifies which return policy actually applies to this purchase' — and names the concrete artifact produced (a policy verdict). An agent knows exactly what this tool answers without opening the schema.

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

Usage Guidelines5/5

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

Gives explicit operating guidance: supply page_text/page_html when you already have the page because the server-side fetch only succeeds on about 1 in 3 US retailers, and names the failure population (large retailers and marketplaces). This is a rare, quantified when-it-works/when-it-doesn't statement.

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

All ReturnCheck 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.

check_return

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources