loopgrid.record_decision

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the essential side-effect boundary: recording evidence only, never executing the proposed action, and optionally recording model output or evaluating a policy. It does not mention persistence confirmation, authority requirements, idempotency, or privacy-mode effects, which is a gap for a write-oriented tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences front-load the core purpose, add optional capabilities, and then give a crucial behavioral guardrail. Every sentence earns its place; there is no fluff or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's high parameter count, nested objects, absence of annotations, and the surrounding sibling set, the description is too thin to fully orient an agent. It covers purpose and one exclusions, but it does not differentiate from record_review/record_outcome by name and provides almost no field-level guidance; the output schema only reduces the return-value burden.

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

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

Schema description coverage is 0% and there are 14 parameters, so the description must compensate, but it only hints at model_output and policy_id. Required fields like decision_type and proposed_action, plus important optional fields such as authority, privacy_mode, and idempotency_key, are left entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States an explicit action and resource: 'Capture a consequential AI/agent decision in LoopGrid.' It also distinguishes itself from execution tools by noting 'This records evidence only and does not execute the proposed action,' which separates it from the sibling record_action. The purpose is specific and readily actionable.

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

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

The description gives clear behavioral context: use this to record decisions as evidence and optionally attach model output or evaluate a policy. It also provides a key exclusion—'does not execute the proposed action'—which prevents misuse as an action-execution tool. However, it does not explicitly name alternatives like record_review or record_outcome.

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