Mirsad

record_decision

Record a decision as one unit: capture the rationale, supporting evidence, rejected alternatives, and affected files or plans. Use it to preserve why a choice was made and get back a decision ID.

Instructions

Record a decision as ONE unit: the decision, why it was taken, the evidence behind it, which alternatives were rejected, and what it affects (files, functions, plans). Returns the decision id.

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>",
      "agent": "<agent>"
    },
    "name": "record_decision"
  }
}

Input Schema

Name	Required	Description	Default
`agent`	Yes
`title`	Yes
`effects`	No
`reasons`	No
`entities`	No
`evidence`	No
`description`	No
`alternatives_rejected`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 14, 2026

TDQS

B3.2/5.0

Behavior3/5

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

With no annotations at all, the description carries the full disclosure burden. It does useful work by stating that everything is captured "as ONE unit" (atomicity) and that the call "Returns the decision id" in the absence of an output schema, but it says nothing about duplicate handling, whether re-recording the same title overwrites, permission needs, or persistence side effects.

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 where nearly every clause maps to a distinct payload field, ending with the return value. The only soft waste is the somewhat awkward line-wrapped phrasing, but no sentence is filler.

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 an 8-parameter mutation tool with no annotations, no output schema, and zero schema documentation, the description is adequate but thin. It communicates purpose and return value, yet omits parameter formats, the role of the agent field, and write-behavior semantics an agent would need to call it confidently.

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 0%, so the description must compensate, and it partially does: the decision/description, reasons, evidence, alternatives_rejected, and effects all get plain-language mapping, including examples for effects ("files, functions, plans"). However, the shapes are not clarified (evidence is an array of free-form objects), and the required "agent" parameter is never explained.

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?

Specific verb and resource ("Record a decision") followed by an enumeration of what the record contains: rationale, evidence, rejected alternatives, and affected artifacts. This is far more specific than a tautology, but it never distinguishes itself from siblings like record_outcome, remember_fact, or why, which plausibly overlap in scope.

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 exclusions, and no mention of when a plain fact record (remember_fact) or an outcome record (record_outcome) is the better choice. The agent must infer that this tool is for architectural or design decisions from the name alone.

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

Deploy Server