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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=false. Beyond that, the description discloses the side effects: a card gets painted, the user is prompted with a question, and the current step is recorded, plus an instruction to follow whatever instructions the tool returns. It does not say what happens on repeat calls despite the idempotent hint, but the write behavior is clear.

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 sentences, front-loaded with what the call does, then when to use it, then alternatives and next steps; each sentence carries distinct information. It is slightly dense because the action, the usage triggers and the routing are packed together, but nothing is redundant.

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?

With zero parameters and an output schema present, the description does not need to explain return values, and it explicitly tells the agent to follow the returned instructions. It covers side effects, usage triggers and the handoff to sibling tools, which is sufficient for a simple entry-point tool.

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 tool takes no parameters, so the baseline applies and nothing about arguments needs explaining. The description correctly does not invent parameter semantics.

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 gives concrete verbs and a resource: it starts MemoryBrain onboarding, paints the first card (which asks the user a work-related question), and records that the user is at that step. That is specific enough for an agent to know what the call does, though it sits oddly against the name 'get_onboarding_status', which suggests a read-only status lookup while the description (and readOnlyHint=false) describes a write.

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?

It states explicitly when to use it ('crear, configurar, probar o empezar su Open Brain, o pregunte qué es o cómo funciona') and names the alternative for the opposite case: use get_context if the user already has a brain and wants to resume work. It also routes follow-up steps to onboarding_step and feed_brain, so the agent knows this is only the entry point.

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