setup_start

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

Annotations already communicate readOnlyHint=true and destructiveHint=false, so the safety burden is minimal. The description adds useful behavioral context: it is a one-time opener, returns the first question rather than an answer, and implies that later steps go through sibling tools. There is no contradiction with annotations because the 'session' is conversational, not a persistent data write.

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?

Two sentences with no wasted words. The first sentence delivers the core action and return value; the second provides the placement rule. The most decision-relevant information is fully front-loaded.

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?

For a zero-parameter tool with an output schema and non-destructive annotations, the description is complete. It captures purpose, result, and sequencing constraints; nothing needed to call this tool correctly is missing.

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?

The input schema declares no parameters, so there is nothing for the description to add at the parameter level. The zero-parameter baseline of 4 applies, and the description correctly focuses on behavior instead.

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?

The description states it 'Starts a new conversational setup session' and specifies the concrete return value: 'the first question, with options and a recommended default.' This clearly disambiguates it from later-step siblings like setup_answer and setup_apply.

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?

Usage is explicitly scoped: 'Use this once, at the very beginning' and a strong when-not condition: 'never mid-conversation once a session is already in progress.' The agent knows exactly when this tool belongs in the flow.

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