Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

manage_protection_outcomes

Record and list real inspection, test, or field outcome observations for a protected board configuration, capturing evidence, causal status, and defect state.

Instructions

Record and read real outcome observations for a protected board configuration (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": {
      "action": "<action>"
    },
    "name": "manage_protection_outcomes"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoinspection | test | field_return | rework | deviation. Default: "".
notesNoOptional free-text notes kept verbatim with the observation for ``record_observation``; empty stores none. Default: "".
stateNoobserved_ok | observed_defect | inconclusive | not_run. Default: "".
actionYes``record_observation`` or ``list_observations``.
observed_onNoISO date the observation was made (not future). Default: "".
causal_statusNoreported | observed | hypothesized | supported | confirmed | excluded | unresolved. Default: "reported".
evidence_gradeNounverified_report | operator_attestation | machine_record | reviewed_inspection | controlled_test | failure_analysis_supported | authorized_disposition. Default: "unverified_report".
source_event_idNoStable idempotency key for this event (e.g. ``inspection:WO-1042:unit7``); retries never duplicate. Default: "".
evidence_case_idNoThe controlled configuration case the outcome belongs to. Default: "".
article_referenceNoOpaque unit/panel/lot reference. Default: "".
evidence_referenceNoPointer to the inspection/test record. Default: "".
observation_windowNoWhen in the lifecycle it was observed (e.g. ``post-cure``, ``after-500h-field``). Default: "".
execution_referenceNoPointer to the run/work order executed. Default: "".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changedv1.5.1
    • addedInput schema / properties / action / description
      Added value: +"``record_observation`` or ``list_observations``."
    • changedInput schema / properties / article_reference / description
      Previous value: -"Default: \"\"."New value: +"Opaque unit/panel/lot reference. Default: \"\"."
    • changedInput schema / properties / causal_status / description
      Previous value: -"Default: \"reported\"."New value: +"reported | observed | hypothesized | supported | confirmed | excluded | unresolved. Default: \"reported\"."
    • changedInput schema / properties / evidence_case_id / description
      Previous value: -"Default: \"\"."New value: +"The controlled configuration case the outcome belongs to. Default: \"\"."
    • changedInput schema / properties / evidence_grade / description
      Previous value: -"Default: \"unverified_report\"."New value: +"unverified_report | operator_attestation | machine_record | reviewed_inspection | controlled_test | failure_analysis_supported | authorized_disposition. Default: \"unverified_report\"."
    • changedInput schema / properties / evidence_reference / description
      Previous value: -"Default: \"\"."New value: +"Pointer to the inspection/test record. Default: \"\"."
    • changedInput schema / properties / execution_reference / description
      Previous value: -"Default: \"\"."New value: +"Pointer to the run/work order executed. Default: \"\"."
    • changedInput schema / properties / kind / description
      Previous value: -"Default: \"\"."New value: +"inspection | test | field_return | rework | deviation. Default: \"\"."
    • changedInput schema / properties / notes / description
      Previous value: -"Default: \"\"."New value: +"Optional free-text notes kept verbatim with the observation for ``record_observation``; empty stores none. Default: \"\"."
    • changedInput schema / properties / observation_window / description
      Previous value: -"Default: \"\"."New value: +"When in the lifecycle it was observed (e.g. ``post-cure``, ``after-500h-field``). Default: \"\"."
    • changedInput schema / properties / observed_on / description
      Previous value: -"Default: \"\"."New value: +"ISO date the observation was made (not future). Default: \"\"."
    • changedInput schema / properties / source_event_id / description
      Previous value: -"Default: \"\"."New value: +"Stable idempotency key for this event (e.g. ``inspection:WO-1042:unit7``); retries never duplicate. Default: \"\"."
    • changedInput schema / properties / state / description
      Previous value: -"Default: \"\"."New value: +"observed_ok | observed_defect | inconclusive | not_run. Default: \"\"."
  2. Addedv1.5.0

TDQS

C2.6/5.0
Behavior2/5

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 mostly covered. The description adds the '(Enterprise)' entitlement requirement, which is genuinely useful, but says nothing about whether recorded observations are immutable, what happens on duplicate submission, or what governance (causal_status / evidence_grade ladders) governs them.

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?

A single front-loaded sentence with no filler or restated title. It is efficient, though its brevity borders on under-specification rather than tight writing.

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?

For a 13-parameter tool with no output schema, no nested objects, and a governed evidence domain, one sentence is not enough. It never indicates which parameters combine into a valid record call, what a read returns, or how this fits alongside the other record_*_outcome tools.

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 13 parameters including enums-in-prose (kind, state, causal_status, evidence_grade) are already documented in the schema. The description adds no extra meaning such as which fields are required together for a valid observation or what list_observations filters on, 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?

States a specific verb+resource pair ('Record and read real outcome observations') and scopes it to 'a protected board configuration (Enterprise)'. However, the sibling list contains many near-identical outcome recorders (record_load_outcome, record_magnet_outcome, record_bond_outcome, record_print_outcome), and the description gives no signal about what makes a 'protection' outcome different, so the agent cannot confidently tell it apart from those tools.

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?

There is no when-to-use or when-not-to-use guidance, no mention of the record vs list split other than the word 'record and read', and no pointer to an alternative tool for related observation recording. The agent must infer everything from the 'action' enum in 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