Skip to main content
Glama

Add Decision

add_decision

Record an architecture decision with its rationale and alternatives in the project context so teams can trace why technical choices were made.

Instructions

Log an architecture decision record (ADR) in the project context.

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": {
      "decision": "<decision>",
      "reason": "<reason>"
    },
    "name": "add_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoProject root directory..
reasonYesWhy this decision was made.
decisionYesWhat was decided.
alternativesNoOther options that were considered.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden and mostly fails to: 'Log' implies a persistent write, but it does not say where the record is stored, whether it is appended versus overwritten, whether prior decisions are preserved, or whether context must already be initialized. With an output schema present the return shape needn't be explained, but the mutation semantics remain undisclosed for a write tool.

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; the resource and scope land immediately. It is slightly under-specified rather than padded, which is the better failure mode but leaves no structural room for the guidance an agent needs.

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?

The tool is simple (four flat string params, no nesting) and an output schema exists, so return values need no explanation, keeping the bar low. Still, for a write tool with zero annotations the description says nothing about storage location, prerequisites, or the expected granularity of the decision text, leaving an agent with gaps before calling it.

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 every parameter including the optional 'alternatives' and the defaulted 'path' is already documented in the input schema, establishing the baseline of 3. The description adds no extra meaning about how required 'decision' and 'reason' should be phrased (e.g., one-line summary versus full ADR text) or what 'project context' means for 'path'.

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 resource ('Log an architecture decision record (ADR)') and states where it lands ('in the project context'), which clearly separates it from task, file, or generic context siblings such as add_task or add_to_context_list. It stops short of stating that it appends to a decision log rather than editing an existing ADR, so the sibling differentiation is good but not fully closed.

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 guidance: no indication of what triggers an ADR versus a task, context note, or milestone, and no mention of prerequisites such as init_context or which project the 'path' refers to. The agent must infer usage entirely from the name.

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