Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

prepopulate_fair_draft

Generate an AS9102 FAIR draft from a Kiln evidence case, pulling case and registry data into the forms so the draft starts populated for review.

Instructions

Pre-populate an AS9102 FAIR draft from a Kiln evidence case.

Needs Kiln Enterprise.

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": {
      "evidence_case_id": "<evidence_case_id>"
    },
    "name": "prepopulate_fair_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
unitNoOptional identity of the physical article: ``serial_number``, ``manufacturing_process_reference``. ``unit.serial_number`` is what lets Form 3 rows and hardware insertion records attach.
organizationNoOptional organization identity: ``organization_name``, ``supplier_code``.
use_registryNoWhen ``True`` (the default), also read the local attested identity registry for values not passed inline. ``False`` uses only the inline inputs. Default: true.
order_contextNoOptional order context: ``purchase_order_number``.
part_identityNoOptional customer part identity: ``customer_part_number``, ``customer_part_name``. Omitted, the registry answer is used when ``use_registry`` is on; otherwise the field stays missing.
export_formatsNoOptional file exports to write beside the csv: ``"pdf"`` and/or ``"xlsx"`` (``"excel"`` means ``"xlsx"``), as one string or a list; other values are ignored. Omitted, no files are written. A failed export is reported in ``export_errors`` and never fails the draft.
fai_declarationNoOptional FAI type declaration: ``fai_type`` ("full" or "partial"), ``baseline_part_number``, ``reason``.
output_form_setNoThe numbering the markdown uses: ``"9102C"`` (default) or ``"9102B"``, case-insensitive. Any other value is refused with ``INVALID_FORM_SET``. Default: "9102C".
evidence_case_idYesRequired. The configuration evidence case (from ``manage_supplier_document_evidence`` ``create_case``) the draft is built from.
form2_row_inputsNoOptional list of Form 2 row inputs, one object per attached document revision: ``{"revision_id", "specification_number", "process_code"}``.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv1.5.1
    • addedInput schema / properties / evidence_case_id / description
      Added value: +"Required. The configuration evidence case (from ``manage_supplier_document_evidence`` ``create_case``) the draft is built from."
    • addedInput schema / properties / export_formats / description
      Added value: +"Optional file exports to write beside the csv: ``\"pdf\"`` and/or ``\"xlsx\"`` (``\"excel\"`` means ``\"xlsx\"``), as one string or a list; other values are ignored. Omitted, no files are written. A failed export is reported in ``export_errors`` and never fails the draft."
    • addedInput schema / properties / fai_declaration / description
      Added value: +"Optional FAI type declaration: ``fai_type`` (\"full\" or \"partial\"), ``baseline_part_number``, ``reason``."
    • addedInput schema / properties / form2_row_inputs / description
      Added value: +"Optional list of Form 2 row inputs, one object per attached document revision: ``{\"revision_id\", \"specification_number\", \"process_code\"}``."
    • addedInput schema / properties / order_context / description
      Added value: +"Optional order context: ``purchase_order_number``."
    • addedInput schema / properties / organization / description
      Added value: +"Optional organization identity: ``organization_name``, ``supplier_code``."
    • changedInput schema / properties / output_form_set / description
      Previous value: -"Default: \"9102C\"."New value: +"The numbering the markdown uses: ``\"9102C\"`` (default) or ``\"9102B\"``, case-insensitive. Any other value is refused with ``INVALID_FORM_SET``. Default: \"9102C\"."
    • addedInput schema / properties / part_identity / description
      Added value: +"Optional customer part identity: ``customer_part_number``, ``customer_part_name``. Omitted, the registry answer is used when ``use_registry`` is on; otherwise the field stays missing."
    • addedInput schema / properties / unit / description
      Added value: +"Optional identity of the physical article: ``serial_number``, ``manufacturing_process_reference``. ``unit.serial_number`` is what lets Form 3 rows and hardware insertion records attach."
    • changedInput schema / properties / use_registry / description
      Previous value: -"Default: true."New value: +"When ``True`` (the default), also read the local attested identity registry for values not passed inline. ``False`` uses only the inline inputs. Default: true."
  2. Addedv1.5.0

TDQS

B3.2/5.0
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 writer/non-destructive profile is covered structurally. The description adds genuine value with the 'Needs Kiln Enterprise' entitlement requirement, which annotations do not express. It stops short of disclosing that draft generation also writes CSV/markdown and optional sidecar files, which is a notable side effect for a tool flagged as non-read-only.

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 sentences with the core action front-loaded and the entitlement gate immediately after; nothing is wasted. It is slightly too terse given ten parameters and file-writing side effects, but it is efficiently structured.

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 ten-parameter tool with nested objects, no output schema, and a file-emission side effect, the description says nothing about what the caller receives or that exports can partially fail. Annotations and the rich schema compensate substantially, keeping this adequate rather than deficient. The absence of any sibling differentiation in a crowded FAIR toolset is the main remaining gap.

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%, so all ten parameters including the nested identity objects already carry their own documentation. The description only echoes the required evidence_case_id ('from a Kiln evidence case') and adds no defaults, precedence rules, or examples beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 and artifact: 'Pre-populate an AS9102 FAIR draft' from 'a Kiln evidence case.' That is far more informative than the name alone and tells the agent what gets created. It doesn't distinguish itself from adjacent FAIR siblings such as manage_fair_evidence_bundle, manage_fair_characteristics, or assess_fair_reaccomplishment, so an agent must infer the boundary.

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 Enterprise,' which is a gate, not usage direction. There is no statement of when to call this versus the other FAIR tools, nor when not to call it (e.g., before an evidence case exists). The agent gets a prerequisite but no routing logic.

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