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

Annotations cover the safety profile (readOnlyHint=true, destructiveHint=false, idempotentHint=false), and the description adds substantial context beyond them: the question is sent to an external AI provider, consumes the family's AI allowance, and does not mutate the log. It also enumerates the error outcomes, consistent with the non-idempotent hint.

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?

Front-loaded with the core action and lane, followed by side effects, return values and error codes. Dense but every sentence carries information; the error-code enumeration is long but useful for a tool with no output schema.

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 no output schema, the description takes on the full burden of describing returns ('answer' plus 'guardrail') and failure modes (payment_required, usage_limit_reached, ai_consent_required, rate_limited, advisor_unavailable). An agent has everything needed to call and interpret this 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 single 'question' parameter has 0% schema description coverage, so the schema alone tells the agent nothing about expected content. The description compensates by defining the topic scope (sleep, feeding, routines, drawn from the family's logged data), which is enough to fill the gap.

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 a specific verb (answer) and resource (free-text question about the child's sleep, feeding or routines from the family's logged data), and explicitly scopes the non-clinical lane. This clearly separates it from the log_* write tools and the read tools in the sibling list.

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?

Gives a clear when-to-use (free-text questions answerable from logged data) and an explicit when-not ('it does not diagnose, assess symptoms or advise on medication'). It does not name a sibling alternative for clinical questions, but no sibling covers that case, so the guidance is strong though not fully routing.

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