Skip to main content
Glama
architectural_modeling_workflow

architectural_modeling_workflow

by Lsc1123

decision_record

Records actual user decisions with a retrievable source, preserving project-state accuracy and preventing invented approvals.

Instructions

Record the actual user decision with a retrievable source; never invent user approval.

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": {
      "expected_revision": "<expected_revision>",
      "kind": "<kind>",
      "statement": "<statement>",
      "user_source": "<user_source>"
    },
    "name": "decision_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
statusNocurrent
statementYes
supersedesNo
user_sourceYes
expected_revisionYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already state this is a non-read-only, non-idempotent, non-destructive, closed-world write, so the safety profile is covered. The description adds a genuine behavioral constraint: the recorded decision must trace to a retrievable user source and approval must not be fabricated. It stops short of explaining revision-conflict behavior, retry semantics, or what happens to existing records on write.

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 compact sentence with the prohibition front-loaded alongside the positive instruction; nothing is redundant. Its brevity is efficient, though the terseness contributes to the under-specification noted elsewhere.

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 six-parameter mutation tool with optional revision preconditions and a supersedes list, the description says nothing about concurrency handling (expected_revision), record lifecycle (status/supersedes), or the kind taxonomy. An output schema exists, so return values need not be covered, but the input-side behavior remains substantially undocumented.

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% across six parameters, so the description must carry the burden and largely does not. It clarifies only the spirit of user_source (must be retrievable) and leaves expected_revision, supersedes, status, and the kind enum values entirely unexplained to the schema or the prose.

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 gives a specific verb and resource: record the actual user decision, tied to a retrievable source. It is clear what the tool does, though it does not name or contrast with any sibling tool such as evidence_register, leaving the agent to 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 Guidelines3/5

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

The clause 'never invent user approval' conveys a hard precondition that implicitly scopes the tool to genuine user-supplied decisions, which is useful. However, there is no explicit when-to-use versus when-not-to-use guidance and no mention of alternatives for recording non-user evidence.

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