Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

get_provenance_history

Read-only

Retrieve provenance-log entries to support explainability and audit trails, filtered by material, printer, feature class, mapping rule, signal, or date.

Instructions

Return provenance-log entries for explainability.

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": "get_provenance_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoThe most readings to return, the most recent ones; defaults to 100. ``limit_hit`` says when more matched. Default: 100.
materialNoKeep only readings for this material. Empty ignores it. Default: "".
since_isoNoKeep only readings at or after this ISO 8601 timestamp. Empty ignores it. Default: "".
printer_idNoKeep only this printer's readings. Empty ignores it. Default: "".
feature_classNoKeep only readings for this kind of feature (``hole``, ``pin``). Empty ignores the filter. Default: "".
mapping_rule_idNoKeep only readings whose recorded rule id matches exactly. Empty ignores it. Default: "".
originating_signalNoKeep only readings from this kind of signal, by its recorded name (``explicit_caliper_measurement``, ``explicit_natural_language_report``). Empty ignores it. Default: "".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv1.5.1
    • changedInput schema / properties / feature_class / description
      Previous value: -"Default: \"\"."New value: +"Keep only readings for this kind of feature (``hole``, ``pin``).  Empty ignores the filter. Default: \"\"."
    • changedInput schema / properties / limit / description
      Previous value: -"Default: 100."New value: +"The most readings to return, the most recent ones; defaults to 100.  ``limit_hit`` says when more matched. Default: 100."
    • changedInput schema / properties / mapping_rule_id / description
      Previous value: -"Default: \"\"."New value: +"Keep only readings whose recorded rule id matches exactly.  Empty ignores it. Default: \"\"."
    • changedInput schema / properties / material / description
      Previous value: -"Default: \"\"."New value: +"Keep only readings for this material.  Empty ignores it. Default: \"\"."
    • changedInput schema / properties / originating_signal / description
      Previous value: -"Default: \"\"."New value: +"Keep only readings from this kind of signal, by its recorded name (``explicit_caliper_measurement``, ``explicit_natural_language_report``).  Empty ignores it. Default: \"\"."
    • changedInput schema / properties / printer_id / description
      Previous value: -"Default: \"\"."New value: +"Keep only this printer's readings.  Empty ignores it. Default: \"\"."
    • changedInput schema / properties / since_iso / description
      Previous value: -"Default: \"\"."New value: +"Keep only readings at or after this ISO 8601 timestamp.  Empty ignores it. Default: \"\"."
  2. Addedv1.5.0

TDQS

B3/5.0
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 safety behavior is covered. The description's one added behavioral fact is the Kiln Pro entitlement requirement, which is genuinely useful (a call can fail for tier reasons), but it says nothing about ordering, pagination/limit_hit truncation, or result shape mentioned in the schema.

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 short lines, purpose first and the prerequisite second, with no filler. Nothing needs to be cut; the issue is missing content, not excess wording.

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 read-only, 7-filter query tool with no output schema, the definition should at least sketch what a provenance entry contains and how results are truncated. The rich schema compensates for parameter semantics, but the description leaves the returned data and the notion of "provenance" underspecified.

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% and each parameter (limit, material, since_iso, printer_id, feature_class, mapping_rule_id, originating_signal) has its own detailed description including empty-string semantics and defaults. The description adds no interpretation of these filters, so the baseline 3 applies.

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

Purpose3/5

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

The description names a verb and resource ("Return provenance-log entries") and adds a purpose ("for explainability"), but the scope of "provenance" is left ambiguous — it does not indicate that these are calibration/measurement readings, information that only surfaces in the annotation title and parameter names. It also fails to distinguish itself from nearby siblings such as verify_provenance_integrity, get_reflog_entry, or explain_calibration_for_design.

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?

"Needs Kiln Pro" is a useful prerequisite gate, but beyond that there is no when-to-use guidance and no mention of alternatives. An agent cannot tell from this text whether to call this or verify_provenance_integrity / explain_calibration_for_design when asked about calibration traceability.

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