Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

assess_drawing_manufacturability

Predict whether a specific printer can hold a drawing's tolerances before printing. It returns a pass, marginal or fail verdict per dimension and can rank multiple machines best first.

Instructions

The verdict: can this machine hold this drawing's tolerances?

Needs Kiln Business.

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": {
      "intake_id": "<intake_id>"
    },
    "name": "assess_drawing_manufacturability"
  }
}

Input Schema

NameRequiredDescriptionDefault
materialNoMaterial for the assessment (e.g. "PLA", "PETG-CF"). When omitted, falls back to the drawing's title-block material callout (the customer's requirement outranks a hint), then to the material set at intake. Default: "".
quantityNoOrder quantity — scales the scrap plan. Default: 1.
design_idNoFile the verdict against this design. Optional — inferred from the attached CAD when it belongs to one. Default: "".
intake_idYesAn intake with a submitted extraction.
printer_idNoThe machine to assess against (as used in your calibration history, e.g. "default"). Default: "".
printer_idsNoRank these registered machines for this drawing instead of assessing the one in ``printer_id``; the answer orders them best first.
verdict_policyNoThis shop's own quality bar — what fraction of printed parts must come out within the drawing's tolerances before a dimension is labeled "pass", e.g. ``{"pass_yield": 0.99, "marginal_yield": 0.9}`` means "pass = we predict at least 99 in 100 parts land in spec; below 90 in 100 is a fail". Fractions in (0,1), marginal below pass; either key may be omitted to keep its default. Moves ONLY the pass/marginal/fail labels; every predicted number is computed identically, and the report states the bar it used. Omitted → the org's saved bar (if one was remembered) → product defaults.
remember_policyNoPersist this call's bar as the org's saved default — set once, applied to every future assessment from any surface (stored account-side, not on this machine). With ``verdict_policy`` omitted, clears the saved bar back to product defaults. Default: false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv1.5.1
    • changedInput schema / properties / design_id / description
      Previous value: -"Default: \"\"."New value: +"File the verdict against this design. Optional — inferred from the attached CAD when it belongs to one. Default: \"\"."
    • addedInput schema / properties / intake_id / description
      Added value: +"An intake with a submitted extraction."
    • changedInput schema / properties / material / description
      Previous value: -"Default: \"\"."New value: +"Material for the assessment (e.g. \"PLA\", \"PETG-CF\"). When omitted, falls back to the drawing's title-block material callout (the customer's requirement outranks a hint), then to the material set at intake. Default: \"\"."
    • changedInput schema / properties / printer_id / description
      Previous value: -"Default: \"\"."New value: +"The machine to assess against (as used in your calibration history, e.g. \"default\"). Default: \"\"."
    • addedInput schema / properties / printer_ids / description
      Added value: +"Rank these registered machines for this drawing instead of assessing the one in ``printer_id``; the answer orders them best first."
    • changedInput schema / properties / quantity / description
      Previous value: -"Default: 1."New value: +"Order quantity — scales the scrap plan. Default: 1."
    • changedInput schema / properties / remember_policy / description
      Previous value: -"Default: false."New value: +"Persist this call's bar as the org's saved default — set once, applied to every future assessment from any surface (stored account-side, not on this machine). With ``verdict_policy`` omitted, clears the saved bar back to product defaults. Default: false."
    • addedInput schema / properties / verdict_policy / description
      Added value: +"This shop's own quality bar — what fraction of printed parts must come out within the drawing's tolerances before a dimension is labeled \"pass\", e.g. ``{\"pass_yield\": 0.99, \"marginal_yield\": 0.9}`` means \"pass = we predict at least 99 in 100 parts land in spec; below 90 in 100 is a fail\". Fractions in (0,1), marginal below pass; either key may be omitted to keep its default. Moves ONLY the pass/marginal/fail labels; every predicted number is computed identically, and the report states the bar it used. Omitted → the org's saved bar (if one was remembered) → product defaults."
  2. Addedv1.5.0

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact, the Kiln Business plan requirement, but says nothing about the fact that a non-read-only tool can persist org-wide state, nor about cost, latency, or what happens when the assessment cannot be computed.

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?

Two short lines, with the core question front-loaded before the prerequisite. Nothing is padded, though the second line is telegraphic enough that it reads more like a tag than an explanation.

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

Completeness2/5

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

With 8 parameters, a nested verdict_policy object, and no output schema, the description carries the burden of explaining what comes back: a verdict, per-dimension pass/marginal/fail labels, and an ordered machine ranking when printer_ids is supplied. None of that is stated, and the org-level persistence behavior of remember_policy is left entirely to the schema.

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 description coverage is 100%, including the intricate verdict_policy semantics and the printer_id vs printer_ids ranking switch, so the baseline of 3 applies. The description itself contributes no parameter meaning beyond the schema, not even a note that printer_ids changes the response into a ranked list.

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 verdict: can this machine hold this drawing's tolerances?" gives a specific question the tool answers, tied to a named artifact (drawing) and a named subject (machine). It is clear what the tool does, but it never names or distinguishes itself from adjacent analysis tools such as tolerance_stack_analysis, analyze_printability, or check_capability.

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?

The only guidance is the prerequisite "Needs Kiln Business", which tells the agent about plan gating rather than when to reach for this tool over alternatives. There is no statement of when-not-to-use, no mention of what an intake must contain first, and no routing to sibling tools that also evaluate printability or tolerances.

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