Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

verify_design_release

Read-only

Verify a signed 3D design release's signature and, optionally, detect tampering by recomputing its mesh fingerprint, assembly-manual hash, or measured spec record.

Instructions

Verify a release's signature and (optionally) its mesh fingerprint, embedded assembly-manual hash, and measured spec record.

Needs Kiln Pro.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "verify_design_release"
  }
}

Input Schema

NameRequiredDescriptionDefault
design_idNoId of the design, for a lookup by release name; used only with ``release_name`` and only when ``release_id`` is not given.
release_idNoDirect release identifier.
release_nameNoThe release's name, looked up under ``design_id``.
recompute_fingerprintNoWhen true, also recompute the mesh fingerprint from the stored source and compare to the signed fingerprint — detects tampering with the underlying mesh, not just the manifest. Default: false.
recompute_manual_hashNoWhen true AND the release embeds an assembly manual (provenance.assembly_manual present), re-hash the on-disk PDF at ``~/.kiln/release_manuals/<release_id>/assembly_manual.pdf`` and compare to the signed SHA-256. Detects manual tampering or corruption — proves a customer holding a v1.2 kit gets the EXACT bytes that were signed on day 1, not a freshly-regenerated PDF. Result fields: ``manual_present`` (bool), ``manual_hash_ok`` (bool or None when the on-disk PDF can't be read). Default: false.
recompute_receipt_hashNoWhen true AND the release signed a measured spec record, re-read that version's record from THIS machine's design library and compare it to the hash in the signed manifest. Detects a measured record that changed after it was signed — a verdict edited, a check removed. Result fields: ``spec_receipt_present`` (bool), ``spec_receipt_hash_ok`` (bool, or None when the record can't be read here), ``spec_receipt_reason`` (why, whenever the answer isn't a plain yes). **Bounds worth stating out loud:** this checks the record against the library on the machine running it — the signer's own. The detailed record does not travel with the release, so a buyer holding only the certificate cannot run this check; what they can verify is the signature and the summary it carries. Default: false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv1.5.1
    • addedInput schema / properties / design_id / description
      Added value: +"Id of the design, for a lookup by release name; used only with ``release_name`` and only when ``release_id`` is not given."
    • changedInput schema / properties / recompute_fingerprint / description
      Previous value: -"Default: false."New value: +"When true, also recompute the mesh fingerprint from the stored source and compare to the signed fingerprint — detects tampering with the underlying mesh, not just the manifest. Default: false."
    • changedInput schema / properties / recompute_manual_hash / description
      Previous value: -"Default: false."New value: +"When true AND the release embeds an assembly manual (provenance.assembly_manual present), re-hash the on-disk PDF at ``~/.kiln/release_manuals/<release_id>/assembly_manual.pdf`` and compare to the signed SHA-256.  Detects manual tampering or corruption — proves a customer holding a v1.2 kit gets the EXACT bytes that were signed on day 1, not a freshly-regenerated PDF.  Result fields: ``manual_present`` (bool), ``manual_hash_ok`` (bool or None when the on-disk PDF can't be read). Default: false."
    • changedInput schema / properties / recompute_receipt_hash / description
      Previous value: -"Default: false."New value: +"When true AND the release signed a measured spec record, re-read that version's record from THIS machine's design library and compare it to the hash in the signed manifest.  Detects a measured record that changed after it was signed — a verdict edited, a check removed.  Result fields: ``spec_receipt_present`` (bool), ``spec_receipt_hash_ok`` (bool, or None when the record can't be read here), ``spec_receipt_reason`` (why, whenever the answer isn't a plain yes). **Bounds worth stating out loud:** this checks the record against the library on the machine running it — the signer's own. The detailed record does not travel with the release, so a buyer holding only the certificate cannot run this check; what they can verify is the signature and the summary it carries. Default: false."
    • addedInput schema / properties / release_id / description
      Added value: +"Direct release identifier."
    • addedInput schema / properties / release_name / description
      Added value: +"The release's name, looked up under ``design_id``."
  2. Addedv1.5.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds the Kiln Pro tier requirement and the optional verification scope, but does not describe return behavior, failure modes, or what happens when a signature or check fails. That is adequate but not rich beyond 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?

Two sentences, front-loaded with purpose and followed by the prerequisite. The parenthetical enumeration is dense but every phrase carries meaning; no filler.

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

Completeness3/5

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

For a six-parameter verification tool with no output schema, the definition is thin: it does not explain the verification result shape, error or failure handling, or how to interpret a failed check. The rich parameter schema and read-only annotations compensate partially, but the top-level description leaves an agent without full return-value context.

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 six parameters are fully documented in the schema. The description's parenthetical list maps roughly to the three optional recompute checks but does not add syntax, defaults, or selection logic beyond what the schema already provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('Verify') and resource ('a release's signature'), and enumerates the optional integrity checks. It stops short of naming which sibling verification tool to use (e.g., verify_feature_release or verify_decoration_preset_release), so it is clear but not fully differentiated.

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

Usage Guidelines2/5

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

Only 'Needs Kiln Pro' is provided as a prerequisite; there is no guidance on when to choose this tool over verify_feature_release, verify_manual_authenticity, or sign_design_release, nor when to enable the optional recompute flags. The agent must infer usage from the schema.

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

Deploy Server

Other Tools