Skip to main content
Glama

apex-dev

Work grade

work_grade
Read-onlyIdempotent

Grade any AI agent work deliverable before releasing escrow (ERC-8183 / G2 Jobs / MCP): checks JSON/schema validity, anti-refusal/stub quality, embedded indirect prompt injection, secret/PII leakage, and task alignment, returning an Ed25519-signed PASS_RELEASE / REVISE / REJECT_REFUND attestation verifiable offline via /.well-known/jwks.json. Free interactive tester (10/day): https://apexfaucet.xyz/grade/ . $0.004 per call over x402 or X-API-Key. Call once without payment for terms, then call again with payment.

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": {
      "task": "<task>",
      "output": "<output>"
    },
    "name": "work_grade"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesTask specification the worker agent was hired to complete.
jobIdNoOptional escrow job ID bound into signed claims.
outputYesDeliverable output produced by the worker agent.
rubricNoOptional evaluation criteria.
paymentNosigned x402 payment payload (PAYMENT-SIGNATURE).
providerNoOptional worker wallet/ID bound into signed claims.
jsonSchemaNoOptional JSON Schema object to validate JSON output against.
useAiJudgeNoOptional: enable Workers AI rubric judge alongside deterministic checks.
expectedFormatNoOptional expected output format.
requiredFieldsNoOptional required JSON keys when output is JSON.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say readOnly/idempotent/openWorld/non-destructive; the description adds substantial context on top: the specific failure classes checked, that the result is a signed attestation verifiable offline via /.well-known/jwks.json, the two-step payment handshake, and pricing ($0.004/call over x402 or X-API-Key, free tester at 10/day). An agent knows cost, auth mode, and side-effect scope before invoking.

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?

Front-loaded with the purpose and the list of checks, then pricing and the payment handshake in a compact form; little is wasted. It is a dense single block, and bundling commercial details (faucet URL, per-call price) with operational guidance makes it slightly harder to scan.

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 10-parameter, multi-check grading tool with no output schema, the description covers what is evaluated, the three possible verdicts, signature verification, and the payment flow, which is most of what an agent needs. It does not describe the shape of the attestation payload or whether jobId/provider are required for escrow-bound grading, a minor gap given no output schema exists.

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; the description earns above that by explaining the `payment` parameter's protocol semantics — the first call returns terms, the second carries PAYMENT-SIGNATURE — which is not evident from the field name alone. It does not go further into how `rubric`, `useAiJudge`, or `expectedFormat` interact with the checks, leaving those to 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?

Specific verb 'Grade' applied to a specific resource ('AI agent work deliverable'), with the exact checks enumerated (schema validity, anti-refusal/stub, prompt injection, secret/PII leakage, task alignment) and the exact return artifact named (Ed25519-signed PASS_RELEASE/REVISE/REJECT_REFUND attestation). This distinguishes it cleanly from nearby siblings like agent_card_grade, delivery_score, and prompt_guard without needing their schemas.

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 a clear trigger condition — grade a deliverable 'before releasing escrow' — and an explicit procedural rule: call once without `payment` for terms, then again with `payment`. It stops short of naming exclusions or alternatives (e.g., when to prefer agent_card_grade or delivery_score instead), so an agent must infer sibling routing.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources