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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add context — and it does: the values are computed by Vitalli from the user's own data, the PhenoAge component uses the published Vora-lab formula and can be distorted by certain factors, and the fitness component only appears with a connected wearable. The closing 'statistical estimates, not a medical assessment' caveat is exactly the kind of framing an agent needs before relaying results. Slightly short of a 5 because it doesn't note what happens with missing cross-app data.

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?

A single sentence with the aggregate purpose front-loaded, followed by a semicolon-delimited inventory of components and a closing caveat — no filler. The component list is dense but each clause maps to a distinct piece of returned data, so it earns its length; it could be broken into two sentences for readability.

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 effectively carries the return-value burden, and it does so by naming each score and its source app plus the conditional fitness component. Combined with the read-only annotations and zero-param schema, an agent has enough to call it correctly; only edge cases (missing wearable, absent Still/Stackwell data) are left implicit.

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 zero parameters, so there is nothing for the description to disambiguate and the 4 baseline applies. The 'signed-in user' phrasing usefully confirms the implicit scoping — no user or date argument is accepted or needed.

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 and resource ('Get the signed-in user's cross-app longevity overview') and then enumerates exactly what the overview is composed of: composite score, PhenoAge vs chronological age, fasting adherence from Still, supplement stack score from Stackwell, and an optional fitness component. That decomposition makes it clearly distinguishable from the narrower sibling reads like stackwell_get_adherence or still_get_fasting_summary, which return only one input to this aggregate.

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 'cross-app ... overview' framing implies this is the aggregate view rather than the per-domain tools, but the description never explicitly says when to call this instead of still_get_fasting_summary or stackwell_get_supplement_stack. It also doesn't state prerequisites beyond the implicit 'signed-in user'. Usage is inferable but not spelled out.

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