Conduit Agentic Commerce

Payment mandate (AP2)

payment_mandate

Destructive

AP2 spend mandates. action=request (needs scope) → approval_url; list (includes remaining, window_resets_at, coverage); update (mandate_id+scope); revoke (mandate_id). update NEVER approves. Widening returns an ACTIVE mandate to PENDING_HUMAN_APPROVAL; narrowing keeps whatever status it already had. monthly_cap is a rolling 30-day window from create. Same category set as a live mandate replaces it at approval and keeps this period's spend. No covering mandate at checkout is handoff, not an error.

Input Schema

TableJSON Schema

Name	Required	Description
`scope`	No	Spend limits — required for action=request and action=update
`action`	Yes	request = create mandate (needs scope); list = enumerate; update = change scope (needs mandate_id+scope); revoke = revoke (needs mandate_id)
`expires`	No	Optional ISO-8601 expiry, e.g. 2026-12-31T00:00:00Z
`agent_id`	Yes	Owning agent id
`mandate_id`	No	Mandate id required for update/revoke
`session_token`	No	Session token from agent_authenticate — required whenever agent_id is passed

Output Schema

TableJSON Schema

Name	Required	Description	Default
`hint`	No
`next`	No
`error`	No
`detail`	No
`status`	No
`applied`	No
`mandates`	No
`mandate_id`	No
`approval_url`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 24, 2026
- addedOutput schema / properties / next / properties / args / additionalProperties / anyOf
```
Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "boolean"
+  }
+]
```
- removedOutput schema / properties / next / properties / args / additionalProperties / type
```
Removed value: -"string"
```

Changed2 schema fields changedSep 1, 2026

changedInput schema / properties / scope / properties / categories / description

Previous value: -"Optional category allowlist, Google Product Taxonomy level 1. Omit or pass [] to allow every category. Accepts the slug, the label, or the GPT numeric id. Slugs: electronics, office-supplies, business-and-industrial, hardware, furniture, home-and-garden, cameras-and-optics, software, media, apparel-and-accessories, luggage-and-bags, health-and-beauty, food-beverages-and-tobacco, sporting-goods, toys-and-games, baby-and-toddler, animals-and-pet-supplies, vehicles-and-parts, arts-and-entertainment, religious-and-ceremonial, mature. Enforced at order_execute: an offer Conduit cannot classify is blocked (shortfall category_unknown), not assumed in scope."New value: +"Optional category allowlist, Google Product Taxonomy level 1. Omit or pass [] for a General mandate (catch-all for unmatched and unclassified offers). Accepts the slug, the label, or the GPT numeric id. Slugs: electronics, office-supplies, business-and-industrial, hardware, furniture, home-and-garden, cameras-and-optics, software, media, apparel-and-accessories, luggage-and-bags, health-and-beauty, food-beverages-and-tobacco, sporting-goods, toys-and-games, baby-and-toddler, animals-and-pet-supplies, vehicles-and-parts, arts-and-entertainment, religious-and-ceremonial, mature. Most specific covering mandate wins; unknown category uses General; no covering mandate is handoff."

changedInput schema / properties / scope / properties / monthly_cap / description

Previous value: -"Max spend this calendar month, e.g. 500"New value: +"Max spend in a rolling 30-day window from when the mandate was created, e.g. 500"

Changed1 schema field changedAug 31, 2026

changedInput schema / properties / scope / properties / categories / description

Previous value: -"Optional category allowlist (empty = all categories)"New value: +"Optional category allowlist, Google Product Taxonomy level 1. Omit or pass [] to allow every category. Accepts the slug, the label, or the GPT numeric id. Slugs: electronics, office-supplies, business-and-industrial, hardware, furniture, home-and-garden, cameras-and-optics, software, media, apparel-and-accessories, luggage-and-bags, health-and-beauty, food-beverages-and-tobacco, sporting-goods, toys-and-games, baby-and-toddler, animals-and-pet-supplies, vehicles-and-parts, arts-and-entertainment, religious-and-ceremonial, mature. Enforced at order_execute: an offer Conduit cannot classify is blocked (shortfall category_unknown), not assumed in scope."

Changed8 schema fields changedAug 29, 2026

removedInput schema / properties / scope / properties / maxPerOrder

Removed value: -{
-  "description": "Max USD (or order currency) per single order, e.g. 50",
-  "type": "number"
-}

addedInput schema / properties / scope / properties / max_per_order

Added value: +{
+  "description": "Max USD (or order currency) per single order, e.g. 50",
+  "type": "number"
+}

removedInput schema / properties / scope / properties / monthlyCap

Removed value: -{
-  "description": "Max spend this calendar month, e.g. 500",
-  "type": "number"
-}

addedInput schema / properties / scope / properties / monthly_cap

Added value: +{
+  "description": "Max spend this calendar month, e.g. 500",
+  "type": "number"
+}

removedOutput schema / properties / approvalUrl
```
Removed value: -{
-  "type": "string"
-}
```
addedOutput schema / properties / approval_url
```
Added value: +{
+  "type": "string"
+}
```
removedOutput schema / properties / mandateId
```
Removed value: -{
-  "type": "string"
-}
```
addedOutput schema / properties / mandate_id
```
Added value: +{
+  "type": "string"
+}
```

Changed1 schema field changedAug 10, 2026

addedInput schema / properties / session_token

Added value: +{
+  "description": "Session token from agent_authenticate — required whenever agent_id is passed",
+  "type": "string"
+}

AddedJul 26, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds substantial behavioral context: the approval flow for widening vs narrowing, the rolling 30-day window for monthly_cap, the replacement behavior for same category sets, and the handoff-not-error note. These go beyond annotations and materially help an agent predict outcomes.

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?

The description is a single dense paragraph packed with essential details. It is not verbose, but the heavy use of semicolons and parentheticals makes it slightly harder to scan quickly. Still, every sentence contributes actionable information, so it earns a 4.

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?

Given the tool has an output schema (not shown) and 6 parameters with nested objects, the description covers all necessary usage context: action requirements, edge cases, status transitions, and error interpretation. It even explains the rolling window and replacement semantics. Nothing critical for correct invocation is missing.

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

Parameters4/5

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

Schema coverage is 100%, so each parameter already has a description. The description adds action-specific semantics (e.g., scope required for request/update, mandate_id for update/revoke) and explains behavior like update NEVER approves, which enriches understanding beyond the schema. It does not fully detail every parameter's format, but the schema handles that, so a 4 is appropriate.

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?

The description clearly states the tool manages AP2 spend mandates and enumerates the four actions (request, list, update, revoke) with their specific purposes. It distinguishes itself from the broader sibling set (orders, inventory, supply) by focusing solely on spend mandates, so an agent can immediately recognize its role.

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?

The description gives explicit per-action requirements: request needs scope, update needs mandate_id+scope, revoke needs mandate_id. It also clarifies critical behavioral rules (update NEVER approves, widening vs narrowing status effects) and error semantics (no covering mandate at checkout is handoff, not an error). This is explicit guidance on when and how to use each action.

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

All Conduit Agentic Commerce 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.

Resources

Need Help?