Skip to main content
Glama

WAI Quantum job service

Attest a job another host ran

attest_quantum_job
Read-onlyIdempotent

Sign off a job another host sealed (the job service, a provider, another person's machine), after verifying it: its receipt and every rule of its form, any verdict or compile it seals worked out again, and, given a trust list and a time, its key held to them (the provider protocol's section 8.8). A job that is not valid is refused and nothing is sealed. Then what its answer must do (intent) is checked against it by the strongest layer the engine has, and the job's digest, the intent and the verdict are sealed with the service's key (wai.quantum.signoff/1). attested, beside the sign-off and outside its seal, says what the job was checked against. verify_quantum_result works the sign-off out again. Verifying the job and checking the intent are held to the service's bounds, and an attestation past them is refused with the local command (wai-quantum attest).

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": {
      "job": "<job>"
    },
    "name": "attest_quantum_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobYesThe job as its host returned it: {"request", "result"}, the result with its receipt; its text is best.
at_msNoA time to hold the receipt to, in milliseconds since 1970.
trustNoA trust list to hold the job's key to: a key set as the job service publishes it at /.well-known/wai-quantum-receipt-keys, as an object or its text.
intentNoWhat the job's answer must do: one intent or a list, as signoff_quantum_job takes it. Left out: the job's own sealed verdict is signed off.
skew_msNoWith at_ms, how many milliseconds after it a receipt's issue may be.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

The annotations only declare readOnly/idempotent/closed-world, so the description carries the real weight and does: it enumerates the verification steps (receipt, every rule of its form, re-running the sealed verdict or compile, key held to trust list per protocol §8.8), the refusal behavior, and the sealed payload format wai.quantum.signoff/1 with the `attested` field placed outside the seal. The only wobble is 'sealed with the service's key', which reads slightly like a write operation against readOnlyHint=true; in context it is signing a returned object, but it costs a beat of clarity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the middle sentence is a run-on with stacked subordinate clauses and parentheticals ('any verdict or compile it seals worked out again, and, given a trust list and a time, its key held to them...') that an agent must re-parse. Dense is fine; hard to parse is not.

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 verification-and-signing tool with an output schema, the description covers the preconditions, the failure mode, the trust/time inputs, and the shape of the returned sign-off, so an agent knows enough to call it once and read the result. What is missing is any statement about cost or latency of the verification bounds, which matters for a tool that re-executes compiled work.

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 100%, so the schema already documents all five parameters, and the description adds only modestly beyond it — mainly the default behavior when `intent` is omitted ('the job's own sealed verdict is signed off') and the fact that `intent` is judged by 'the strongest layer the engine has'. The `at_ms`/`skew_ms` and `trust` semantics are restated or already in 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?

Opens with a specific verb and object ('Sign off a job another host sealed') and scopes the resource to jobs produced elsewhere — the job service, a provider, another machine. It also distinguishes itself from the re-derivation path by naming verify_quantum_result, so an agent can tell which of the two it wants without opening a schema.

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?

Establishes the precondition (the job was sealed by another host, and you have a trust list and a time) and the outcome when the precondition fails ('A job that is not valid is refused and nothing is sealed'). It also sets a boundary against the local fallback ('an attestation past them is refused with the local command'), but it never states when an agent should prefer this over simply running the job itself with run_quantum_circuit, which is the most likely confusion.

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