EUCompliance Tools - Invoice Guard & Agent Evidence

AgentLLM Plus inference

agentllm_plus

Read-only

OpenAI-compatible stronger drafting, analysis and longer summaries for exactly 0.02 USDC per call. Run prepare_agentllm with tier plus first. Hard limits are 6,000 UTF-8 input bytes, 16 messages and 1,200 output tokens; upstream model and usage are disclosed and the result includes a signed receipt.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "agentllm_plus"
  }
}

Input Schema

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

Output Schema

Name	Required	Description
`id`	No
`tool`	No
`error`	No
`model`	No
`usage`	No
`object`	No
`charged`	No	When present on an error, false means the failed result is uncharged.
`choices`	No
`created`	No
`message`	No
`missing`	No
`receipt`	No
`settled`	No	When present on an error, false means no settlement occurred.
`unknown`	No
`accepted`	No
`retryable`	No
`error_code`	No
`extensions`	No
`status_code`	No
`did_you_mean`	No
`x402_service`	No
`missing_checks`	No
`partial_evidence`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedSep 6, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already mark it read-only and non-idempotent; the description adds valuable behavior beyond that: exact price per call, the mandatory prepare step, hard input/output limits, upstream-model disclosure, and a signed receipt in the result. No contradictions with annotations.

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?

A single dense sentence that front-loads the core capability and price, then adds the prerequisite and limits. Every clause earns its place; there is no fluff or rephrasing of the schema.

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 output schema covers return shape and annotations cover safety, the description is complete: it states the prerequisite, cost, hard limits, model disclosure, and receipt. An agent has enough to decide and invoke correctly without further lookups.

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 coverage is 0%, so the description carries the burden, but it does not systematically explain prompt, system, and max_tokens. The 'OpenAI-compatible' label supplies standard API semantics and the hard-limit sentence maps input bytes and output tokens to schema constraints, which is helpful but leaves system and the 16-message limit implicit.

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?

States it performs OpenAI-compatible drafting, analysis, and longer summaries — a concrete inference capability — and differentiates itself from the basic/micro siblings by branding itself 'stronger' and 'longer.' The tool name and title are reinforced rather than merely restated.

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?

Gives clear context: use when stronger drafting/analysis/longer summaries are needed and prepays via prepare_agentllm with tier plus first. It does not explicitly name the cheaper siblings as alternatives or state when not to use it, so it stops short of a full when/when-not guide.

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

All EUCompliance Tools - Invoice Guard & Agent Evidence 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.