Delx Wellness Onboarding Flow

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

Annotations already mark the tool readOnly, idempotent, and non-destructive; the description reinforces that with 'does NOT persist anything' and adds the cross-connector profile-sharing behavior. This extra state-model context helps the agent reason about data consistency, with no contradiction of the annotations.

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 the return value and zero filler. The connector list in the final sentence is long but earned, because it communicates a key cross-connector behavior.

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-required-param read tool with no output schema, the description supplies the essential return content, non-persistence guarantee, and the follow-up update tool. It is complete enough to call, though a bit more detail on response_format behavior would round it out.

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 description does not mention locale or response_format at all, and schema coverage is only 50% (response_format has no schema description). The enum values are self-explanatory, but the tool description adds no guidance about defaults or how these params shape the output, so it fails to compensate for the coverage 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?

The description opens with a concrete verb ('Return') and a precise resource: 'the 11-question onboarding flow plus the current profile state and missing fields.' This clearly distinguishes it from read siblings like google_health_get_profile (which lacks the onboarding flow) and from the write sibling google_health_profile_update.

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 sentence 'Pair with google_health_profile_update once the user answers' gives an explicit sequencing rule that routes the agent to the correct sibling after this call. It does not, however, spell out when to prefer this over profile_get/get_profile or state exclusions, so it stops short of full when/when-not coverage.

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