Skip to main content
Glama

decision_record

Read-onlyIdempotent

Generate an Architecture Decision Record from explicit alternatives, the selected decision, and consequences, without inventing acceptance.

Instructions

Generate an ADR from explicit alternatives, decision and consequences. Does not invent acceptance.

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": {
      "title": "<title>",
      "context": "<context>",
      "options": "<options>",
      "decision": "<decision>",
      "consequences": "<consequences>"
    },
    "name": "decision_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYes
statusNoproposed
contextYes
optionsYes
decisionYes
consequencesYes

Output Schema

NameRequiredDescriptionDefault
kindNo
sourcesNo
markdownNo
validatedNo
limitationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • changedInput schema / required
      Previous value: -[
      -  "title",
      -  "context",
      -  "options",
      -  "decision",
      -  "consequences",
      -  "status"
      -]New value: +[
      +  "title",
      +  "context",
      +  "options",
      +  "decision",
      +  "consequences"
      +]
  2. First observedv0.4.1

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The sentence "Does not invent acceptance" adds real behavioral context beyond that — the tool will not auto-promote a decision to accepted status — but it is terse and does not clarify how status selection or document rendering behaves.

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 constraint second; no filler. The second sentence is slightly cryptic in wording, which costs a point on clarity rather than length.

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?

An output schema exists, so return format need not be described, and annotations carry the safety profile. For a six-parameter generator with zero schema descriptions, however, the definition is thin: it omits status semantics and any guidance on what a well-formed context or consequences entry should contain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the parameter burden and largely does not. It names options, decision and consequences (three of six fields) but says nothing about title, context, or the status enum with its 'proposed'/'accepted'/'superseded' values and default — arguably the field most in need of explanation given the acceptance caveat.

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?

"Generate an ADR from explicit alternatives, decision and consequences" names a specific verb and artifact, and enumerates the inputs that produce it. It distinguishes itself from nearby writers like implementation_plan or architecture_diagram implicitly by the ADR artifact, though it never names a sibling directly.

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

Usage Guidelines3/5

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

The phrase "from explicit alternatives, decision and consequences" implies a precondition: the decision is already made and the agent must supply the trade-offs rather than have them discovered. There is no explicit when-not guidance or routing to alternatives (e.g., implementation_plan for execution detail), so usage must be inferred.

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