Conduit Agentic Commerce

Search supply

supply_search

Read-onlyIdempotent

Multi-provider discovery (live REAL merchants by default). Returns a ranked page (default limit=30, max 100) with total/has_more/next_offset. Follow next.args (search_id+offset+limit) to page without re-fanout. Optional fetch_limit (max 300) deepens the upstream pull on new searches. Pass include_sandbox=true only to append DEMO/SANDBOX test merchants at the bottom (test_offer=true). Always pass agent_id for mandate-aware badges. Carry search_id through supply_details / order_execute / order_feedback. Offer descriptions are clean text cut to 350 chars; supply_details returns the full text.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Page size of ranked offers to return (default 30, max 100)
`query`	No	Product search query, e.g. USB-C charger 65W. Required for a new search; omit when paging with search_id + offset
`budget`	No	Max total budget — number means USD; or { amount, currency }
`offset`	No	0-based offset into the ranked set for this search_id (default 0). For page 2+, pass search_id from the prior response and follow next.args
`country`	No	ISO country for ships-to, e.g. US
`agent_id`	No	Agent id for mandate-aware badges (always pass when available)
`quantity`	No	Desired quantity (default 1)
`search_id`	No	Resume paging into a prior ranked set (with offset>0, or offset 0 without query). New searches with query mint a fresh search_id
`fetch_limit`	No	Optional override for per-merchant upstream pull (default max(20, limit*2), max 300). Ignored when paging via search_id+offset
`payable_with`	No	Filter to rails the agent can pay with, e.g. ["x402"]
`session_token`	No	Session token from agent_authenticate — required whenever agent_id is passed
`include_sandbox`	No	Include DEMO/SANDBOX merchants (listed last, test_offer=true). Default false — live REAL merchants only. Use only when testing Conduit checkout flows.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`hint`	No
`next`	No
`error`	No
`limit`	No
`total`	No
`detail`	No
`offers`	No
`offset`	No
`country`	No
`partial`	No
`degraded`	No
`has_more`	No
`withheld`	No
`search_id`	No
`next_offset`	No
`recommended`	No
`badge_counts`	No
`country_default`	No
`include_sandbox`	No
`sandbox_included`	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"
```

Changed15 schema fields changedAug 29, 2026

changedInput schema / properties / include_sandbox / description

Previous value: -"Include DEMO/SANDBOX merchants (listed last, testOffer=true). Default false — live REAL merchants only. Use only when testing Conduit checkout flows."New value: +"Include DEMO/SANDBOX merchants (listed last, test_offer=true). Default false — live REAL merchants only. Use only when testing Conduit checkout flows."

removedOutput schema / properties / badgeCounts
```
Removed value: -{}
```
addedOutput schema / properties / badge_counts
```
Added value: +{}
```

removedOutput schema / properties / countryDefault

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "boolean"
-    }
-  ]
-}

addedOutput schema / properties / country_default

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "boolean"
+    }
+  ]
+}

removedOutput schema / properties / hasMore

Removed value: -{
-  "type": "boolean"
-}

addedOutput schema / properties / has_more
```
Added value: +{
+  "type": "boolean"
+}
```
removedOutput schema / properties / includeSandbox
```
Removed value: -{
-  "type": "boolean"
-}
```
addedOutput schema / properties / include_sandbox
```
Added value: +{
+  "type": "boolean"
+}
```

removedOutput schema / properties / nextOffset

Removed value: -{
-  "anyOf": [
-    {
-      "type": "number"
-    },
-    {
-      "type": "null"
-    }
-  ]
-}

addedOutput schema / properties / next_offset

Added value: +{
+  "anyOf": [
+    {
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

removedOutput schema / properties / sandboxIncluded
```
Removed value: -{
-  "type": "number"
-}
```
addedOutput schema / properties / sandbox_included
```
Added value: +{
+  "type": "number"
+}
```
removedOutput schema / properties / searchId
```
Removed value: -{
-  "type": "string"
-}
```
addedOutput schema / properties / search_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 cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds substantial behavior beyond them: default/max page sizes, response fields (total/has_more/next_offset), the fetch_limit upstream-deepening behavior, sandbox merchants being appended at the bottom with test_offer=true, and the 350-char description truncation. This is rich operational context an agent needs.

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?

Core purpose and the paging contract are front-loaded, and almost every sentence carries operational content. The dense parenthetical stacking (e.g. 'next.args (search_id+offset+limit)') slightly hurts scannability but wastes little.

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?

For a 12-parameter, high-complexity discovery tool with an output schema, the description covers the essential behaviors an agent needs: paging, sandbox behavior, auth via agent_id, and downstream search_id propagation. Nothing critical to 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 the baseline is 3, but the description adds cross-parameter interaction meaning the schema does not: how search_id+offset+limit page together, that fetch_limit is ignored when paging, and the agent_id/search_id carry-through contract. It stops short of explaining budget or payable_with semantics.

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 opens with a specific verb+resource ('Multi-provider discovery') and immediately scopes it ('live REAL merchants by default'), so the agent knows this is the fan-out search entry point. It also explicitly contrasts with sibling supply_details ('supply_details returns the full text'), disambiguating the two.

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?

Explicit when/when-not guidance is present: 'Follow next.args ... to page without re-fanout', 'Pass include_sandbox=true only to append DEMO/SANDBOX test merchants', 'Always pass agent_id', and 'Carry search_id through supply_details / order_execute / order_feedback'. It names the alternative tool and the condition that selects it.

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?