garmin_day

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

Beyond the readOnly/openWorld annotations, it discloses a genuine behavioral trait: results can be marked 'partial' when sections are incomplete, and it warns the agent to inspect section statuses and activity pagination. That is useful non-obvious context for a read-only aggregate; it stops short of describing how partial data is signalled or whether pagination is handled automatically.

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 tight sentences, front-loaded with what is aggregated before the caveat about partial data. Nothing is padded, though the partial-data warning could be marginally more concrete.

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?

An output schema exists, so return values needn't be explained, and readOnly annotations cover safety. What remains missing is the date format and default-date behavior; otherwise the definition gives enough for correct invocation of an aggregate read.

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 parameter has 0% schema description coverage, so the description carries the burden. It only says 'for one date' — no date format (e.g. YYYY-MM-DD), no statement of what happens when the optional date is omitted and the null default applies (presumably today). This is a material gap an agent would need to guess around.

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?

Names a specific action ('Combine') and enumerates the exact resources aggregated (daily summary, sleep, HRV, Body Battery, workouts) scoped to one date. This clearly distinguishes it from the many sibling tools that each fetch a single data type, so an agent can tell it is the aggregate/day view without opening the schema.

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 implied by the aggregation framing plus the advice to check section statuses and activity pagination, which suggests a one-call day rollup. However, it never explicitly says to prefer this over calling garmin_daily_summary, garmin_sleep, garmin_hrv etc. individually, nor does it state when a single-data-type sibling is the better choice.

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