AgentResolver — Agent Commerce Health Monitoring

Procure a compatible capability

procure

Read-onlyIdempotent

CALL THIS when the agent's installed tools do not clearly satisfy the current task. Free open-world procurement across APIs, MCP, x402, L402 and MPP. Required compatibility evidence fails closed: AgentResolver returns no selected provider rather than guessing. When supported unknowns remain, the response can recommend the paid $0.02 verified_resolve step. Never authorizes spend.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`goal`	Yes
`limit`	No
`constraints`	No
`providerOrigins`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedSep 21, 2026

removedInput schema / properties / constraints / description

Removed value: -"Hard procurement constraints. Missing evidence is surfaced as unknown rather than assumed compatible."

removedInput schema / properties / constraints / properties / auth / description
```
Removed value: -"Allowed provider authentication model."
```

removedInput schema / properties / constraints / properties / availableInputSchema / description

Removed value: -"JSON Schema describing the data the caller can provide to the selected capability."

removedInput schema / properties / constraints / properties / maxPriceUsd / description

Removed value: -"Maximum target-provider price in USD that the caller is willing to consider."

removedInput schema / properties / constraints / properties / preferredNetworks / description
```
Removed value: -"Allowed or preferred payment networks, for example eip155:8453."
```

removedInput schema / properties / constraints / properties / protocol / description

Removed value: -"Required provider protocol. Use any when protocol is not a hard constraint."

removedInput schema / properties / constraints / properties / requireHttps / description
```
Removed value: -"Require an HTTPS execution endpoint. Defaults to true."
```

removedInput schema / properties / constraints / properties / requiredOutputSchema / description

Removed value: -"JSON Schema describing the output the caller requires from the selected capability."

removedInput schema / properties / constraints / properties / sideEffect / description
```
Removed value: -"Allowed side-effect class for the selected capability."
```

removedInput schema / properties / goal / description

Removed value: -"Plain-language description of the external capability the agent needs."

removedInput schema / properties / limit / description

Removed value: -"Maximum number of ranked candidates to return. Defaults to 5."

removedInput schema / properties / providerOrigins / description

Removed value: -"Optional provider HTTPS origins already known to the caller. AgentResolver checks only their fixed well-known provider manifest and matching live x402 routes; no arbitrary target is proxied."

Changed13 schema fields changedSep 19, 2026

addedInput schema / properties / constraints / description

Added value: +"Hard procurement constraints. Missing evidence is surfaced as unknown rather than assumed compatible."

addedInput schema / properties / constraints / properties / auth / description
```
Added value: +"Allowed provider authentication model."
```

addedInput schema / properties / constraints / properties / availableInputSchema / description

Added value: +"JSON Schema describing the data the caller can provide to the selected capability."

addedInput schema / properties / constraints / properties / maxPriceUsd / description

Added value: +"Maximum target-provider price in USD that the caller is willing to consider."

addedInput schema / properties / constraints / properties / preferredNetworks / description
```
Added value: +"Allowed or preferred payment networks, for example eip155:8453."
```

addedInput schema / properties / constraints / properties / protocol / description

Added value: +"Required provider protocol. Use any when protocol is not a hard constraint."

changedInput schema / properties / constraints / properties / protocol / enum

Previous value: -[
-  "x402",
-  "mcp",
-  "any"
-]New value: +[
+  "x402",
+  "l402",
+  "mpp",
+  "mcp",
+  "any"
+]

addedInput schema / properties / constraints / properties / requireHttps / description
```
Added value: +"Require an HTTPS execution endpoint. Defaults to true."
```

addedInput schema / properties / constraints / properties / requiredOutputSchema / description

Added value: +"JSON Schema describing the output the caller requires from the selected capability."

addedInput schema / properties / constraints / properties / sideEffect / description
```
Added value: +"Allowed side-effect class for the selected capability."
```

addedInput schema / properties / goal / description

Added value: +"Plain-language description of the external capability the agent needs."

addedInput schema / properties / limit / description

Added value: +"Maximum number of ranked candidates to return. Defaults to 5."

addedInput schema / properties / providerOrigins

Added value: +{
+  "description": "Optional provider HTTPS origins already known to the caller. AgentResolver checks only their fixed well-known provider manifest and matching live x402 routes; no arbitrary target is proxied.",
+  "items": {
+    "format": "uri",
+    "type": "string"
+  },
+  "maxItems": 2,
+  "type": "array"
+}

AddedSep 19, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations already mark it read-only, open-world, idempotent, and non-destructive. The description adds meaningful behavior beyond that: it fails closed rather than guessing, is free, can recommend a paid $0.02 follow-up, and never authorizes spend. No contradiction with annotations exists.

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?

The description is four sentences and front-loads the critical trigger condition. Every sentence contributes useful information: when to call, supported protocols, fail-closed behavior, follow-up recommendation, and spend constraint. There is no filler.

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

Completeness2/5

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

Despite good purpose and behavior coverage, the tool is complex with four parameters and a nested constraints object, and there is no output schema. The description does not explain how to construct the goal, constraints, limit, or providerOrigins, nor what the response contains. An agent would struggle to invoke it correctly with only this description and the bare schema.

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

Parameters1/5

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

Schema description coverage is 0%, so the description carries the full burden of explaining parameters, but it never mentions goal, limit, constraints, or providerOrigins. Terms like 'compatibility evidence' are not tied to any specific input, leaving an agent to guess how to populate the schema.

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 states a specific trigger and resource: call this when installed tools do not clearly satisfy the current task, to procure a compatible capability across APIs, MCP, x402, L402, and MPP. It also distinguishes itself from the verified_resolve step by describing it as a follow-up recommendation rather than this tool's action.

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?

It explicitly tells the agent when to use the tool: when installed tools do not clearly satisfy the task. It also gives guidance on an alternative/follow-up step, recommending the paid verified_resolve when supported unknowns remain, and clarifies that this tool never authorizes spend.

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

All AgentResolver — Agent Commerce Health Monitoring 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.

Procure a compatible capability

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources