AImart Parquet

Verify artifact provenance (free)

verify_provenance

Read-onlyIdempotent

Free. Check that a file this service produced is authentic and unaltered: verifies the post-quantum ML-DSA-65 (NIST FIPS 204) signature in an artifact's provenance, and with artifact_id also re-checks the stored file's hash and size against the signed manifest.

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": {
      "manifest": "<manifest>",
      "signature": "<signature>"
    },
    "name": "verify_provenance"
  }
}

Input Schema

Name	Required	Description
`manifest`	Yes	provenance.manifest exactly as received.
`signature`	Yes	provenance.signature (base64).
`artifact_id`	No	artifact_id returned by an earlier convert_to_parquet call.

Output Schema

Name	Required	Description	Default
`valid`	Yes
`problems`	Yes
`algorithm`	Yes
`file_matches`	No
`signature_valid`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already establish readOnly/idempotent/non-destructive, so the description adds the non-obvious parts: the call is free, the exact cryptographic algorithm and standard being verified, and that `artifact_id` expands the check from signature-only to signature plus stored-bytes integrity. It leaves out what a failure returns, but an output schema is present to carry that.

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 core action and mechanism, then the optional-parameter effect. The leading 'Free.' is short and decision-relevant for cost-sensitive callers; nothing is redundant.

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?

For a three-parameter, read-only verification tool with a full schema and an output schema, the description covers purpose, mechanism, cost, and the optional deeper check. The nested `manifest` object is passed through verbatim as documented, so no further shape explanation is required.

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 baseline is 3, but the description earns above baseline by explaining the semantic role of `artifact_id` — it is not just an identifier but a switch that enables hash and size verification against the signed manifest. That conditional behavior is not derivable from the schema alone.

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 a specific verb and resource ('Check that a file this service produced is authentic and unaltered') and names the concrete mechanism (ML-DSA-65 / FIPS 204 signature over the `provenance` blob). This is plainly distinct from every sibling, which are all parquet conversion/inspection/query tools.

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 conveys the trigger condition — you have an artifact this service produced and want to confirm it wasn't tampered with — and explains the conditional escalation: passing `artifact_id` additionally re-checks the stored file's hash and size. It does not state exclusions (e.g. that it cannot verify third-party artifacts or that it fails when the artifact was deleted), so it stops short of full when/when-not guidance.

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

All AImart Parquet 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.