Agent Decision & Evidence Tools (MCP + x402)

Prepare AgentLLM Micro (free)

prepare_agentllm_micro

Read-onlyIdempotent

FREE validation of the exact AgentLLM prompt, system instruction and token limit before purchase. It enforces the input and output limits without calling a model or charging anything.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`prompt`	Yes
`system`	No
`max_tokens`	No

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	No
`tier`	No
`tool`	No
`error`	No
`model`	No
`price`	No	No payment is required for this tool.
`limits`	No
`charged`	No
`message`	No
`missing`	No
`payment`	No
`settled`	No	When present on an error, false means no settlement occurred.
`unknown`	No
`accepted`	No
`contract`	No
`paid_tool`	No
`retryable`	No
`error_code`	No
`input_bytes`	No
`status_code`	No
`did_you_mean`	No
`ready_to_buy`	No
`message_count`	No
`missing_checks`	No
`paid_arguments`	No
`upstream_called`	No
`fixed_price_usdc`	No
`partial_evidence`	No
`accepted_max_output_tokens`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedSep 6, 2026

addedInput schema / additionalProperties
```
Added value: +false
```
addedInput schema / properties / max_tokens / maximum
```
Added value: +300
```
addedInput schema / properties / max_tokens / minimum
```
Added value: +1
```
removedInput schema / properties / max_tokens / title
```
Removed value: -"Max Tokens"
```
addedInput schema / properties / prompt / maxLength
```
Added value: +6000
```
addedInput schema / properties / prompt / minLength
```
Added value: +1
```
removedInput schema / properties / prompt / title
```
Removed value: -"Prompt"
```
addedInput schema / properties / system / maxLength
```
Added value: +2000
```
removedInput schema / properties / system / title
```
Removed value: -"System"
```

removedInput schema / title

Removed value: -"prepare_agentllm_micro_toolArguments"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "anyOf": [
+    {
+      "required": [
+        "ok",
+        "tier",
+        "model",
+        "input_bytes",
+        "message_count",
+        "accepted_max_output_tokens",
+        "limits",
+        "fixed_price_usdc",
+        "contract",
+        "ready_to_buy",
+        "charged",
+        "upstream_called",
+        "paid_tool",
+        "paid_arguments",
+        "payment",
+        "price"
+      ]
+    },
+    {
+      "required": [
+        "error"
+      ]
+    }
+  ],
+  "description": "Structured result contract for prepare_agentllm_micro. A success satisfies the documented success branch. A domain or tool error includes error and is not a successful settlement; unpaid x402 requirements are carried by the transport wrapper.",
+  "properties": {
+    "accepted": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "accepted_max_output_tokens": {
+      "type": "integer"
+    },
+    "charged": {
+      "type": "boolean"
+    },
+    "contract": {
+      "type": "string"
+    },
+    "did_you_mean": {
+      "additionalProperties": true,
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "error": {
+      "oneOf": [
+        {
+          "type": "string"
+        },
+        {
+          "additionalProperties": true,
+          "properties": {
+            "code": {
+              "type": [
+                "string",
+                "null"
+              ]
+            },
+            "message": {
+              "type": "string"
+            },
+            "param": {
+              "type": [
+                "string",
+                "null"
+              ]
+            },
+            "type": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "message"
+          ],
+          "type": "object"
+        }
+      ]
+    },
+    "error_code": {
+      "type": "string"
+    },
+    "fixed_price_usdc": {
+      "type": "string"
+    },
+    "input_bytes": {
+      "type": "integer"
+    },
+    "limits": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "message": {
+      "type": "string"
+    },
+    "message_count": {
+      "type": "integer"
+    },
+    "missing": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "missing_checks": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "model": {
+      "type": "string"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "paid_arguments": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "paid_tool": {
+      "type": "string"
+    },
+    "partial_evidence": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "payment": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "price": {
+      "const": "free",
+      "description": "No payment is required for this tool.",
+      "type": "string"
+    },
+    "ready_to_buy": {
+      "type": "boolean"
+    },
+    "retryable": {
+      "type": "boolean"
+    },
+    "settled": {
+      "description": "When present on an error, false means no settlement occurred.",
+      "type": "boolean"
+    },
+    "status_code": {
+      "type": "integer"
+    },
+    "tier": {
+      "type": "string"
+    },
+    "tool": {
+      "type": "string"
+    },
+    "unknown": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "upstream_called": {
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

AddedAug 23, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior; the description adds meaningful context by stating it enforces input/output limits and does not call a model or charge anything. This goes beyond the annotations by clarifying side-effect-free validation semantics.

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?

Two sentences, front-loaded with the most important fact (free validation), with zero filler. The first sentence states the exact scope and the second explains the behavioral guarantee without repeating the title.

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

Completeness4/5

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

For a simple 3-parameter tool with an output schema and strong safety annotations, the description supplies the core operational context: what is validated, when it applies, and that it is free/no model call. It does not explain the return shape, but the output schema covers that; no critical gap remains.

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 0%, but the description maps the three relevant concepts (AgentLLM prompt, system instruction, token limit) to the prompt/system/max_tokens parameters. It does not add details on defaults, ranges, or formatting beyond what the schema already provides, so it only partially compensates for the lack of per-parameter descriptions.

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 combination: 'FREE validation of the exact AgentLLM prompt, system instruction and token limit before purchase.' This clearly distinguishes the tool from paid or model-calling siblings like agentllm_basic/agentllm_micro by emphasizing it is a no-cost pre-purchase validation step.

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

Usage Guidelines4/5

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

It gives a clear context: use this before purchasing/using AgentLLM to validate limits, and it explicitly states no model call or charge occurs. It does not name sibling alternatives or state when not to use it, but the 'before purchase' condition is enough to route an agent appropriately.

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

All Agent Decision & Evidence Tools (MCP + x402) 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.