Decide Policy Notaries

Check return eligibility

return_eligibility

Read-onlyIdempotent

Evaluate whether a US consumer subscription purchase can be reversed under versioned source-backed rules. Returns UNKNOWN when required conditions are absent or manual review is required.

Input Schema

TableJSON Schema

Name	Required	Description
`plan`	Yes	Plan type. Currently only 'individual' plans are supported.
`region`	Yes	Region code. Currently only 'US' is supported.
`vendor`	Yes	Vendor identifier (lowercase, underscore-separated).
`days_since_purchase`	Yes	Number of days since the subscription was purchased.
`qualifying_conditions_met`	No	Required when the vendor policy has source-specific conditions such as first purchase, unused benefits, or an eligible annual plan.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`code`	Yes
`method`	No
`vendor`	No
`message`	Yes
`verdict`	Yes
`returnable`	No
`return_type`	No
`source_hash`	No
`evaluated_at`	No
`rules_version`	No
`policy_version`	No
`automation_safe`	No
`policy_evidence`	No
`rulebook_result`	No
`required_context`	No
`policy_source_url`	No
`return_window_days`	No
`days_since_purchase`	No
`policy_last_checked`	No
`policy_source_notes`	No
`policy_last_verified_utc`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 6, 2026
- changedOutput schema / properties / policy_last_verified_utc / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```

Changed3 schema fields changedSep 6, 2026

addedOutput schema / properties / automation_safe
```
Added value: +{
+  "type": "boolean"
+}
```

addedOutput schema / properties / policy_evidence

Added value: +{
+  "additionalProperties": true,
+  "properties": {
+    "checked_at": {
+      "type": "string"
+    },
+    "current": {
+      "type": "boolean"
+    },
+    "evaluated_at": {
+      "type": "string"
+    },
+    "policy": {
+      "enum": [
+        "refund",
+        "cancel",
+        "return",
+        "trial"
+      ],
+      "type": "string"
+    },
+    "policy_version": {
+      "type": "string"
+    },
+    "reason": {
+      "type": "string"
+    },
+    "schema_version": {
+      "enum": [
+        "policy_evidence_v1"
+      ],
+      "type": "string"
+    },
+    "snapshot_generated_at": {
+      "type": "string"
+    },
+    "snapshot_hash": {
+      "type": "string"
+    },
+    "source_hash": {
+      "type": "string"
+    },
+    "source_url": {
+      "type": "string"
+    },
+    "status": {
+      "enum": [
+        "current",
+        "expired",
+        "unavailable",
+        "review_required"
+      ],
+      "type": "string"
+    },
+    "valid_until": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "vendor": {
+      "type": "string"
+    },
+    "verified_at": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "schema_version",
+    "policy",
+    "vendor",
+    "status",
+    "reason",
+    "current",
+    "evaluated_at"
+  ],
+  "type": "object"
+}

changedOutput schema / properties / returnable / type

Previous value: -"boolean"New value: +[
+  "boolean",
+  "null"
+]

First observedJul 16, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare the operation read-only, idempotent, and non-destructive, so the safety profile is covered. The description adds one genuinely useful behavioral note, the UNKNOWN fallback when conditions are absent or manual review is required, but nothing about the versioned-rule sourcing or what triggers manual review.

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?

Two sentences, front-loaded with purpose and followed by the key output caveat; nothing is wasted. Slightly terse for the disambiguation burden this tool carries, but structurally clean.

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

Completeness3/5

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

An output schema exists so return values need not be re-explained, and annotations cover the safety profile. However, the description does not disambiguate from the near-identical sibling refund_eligibility, which is the main thing an agent needs in this family.

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 100%, so the schema already documents all five parameters including the enum constraints and the conditional nature of qualifying_conditions_met. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Evaluate') and resource ('whether a US consumer subscription purchase can be reversed'). The scope is clear, but it never distinguishes itself from the sibling refund_eligibility, which reads almost identically to an agent choosing between them.

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

Usage Guidelines2/5

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

There is no when-to-use guidance and no mention of the obvious alternatives (refund_eligibility, cancellation_penalty, trial_terms). An agent must infer which sibling applies from the name alone, which is risky given how similar these four are.

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

All Decide Policy Notaries 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.