get_morning_brief

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

With no annotations, the description carries the burden and does meaningful work: it discloses scope exclusions (no alerts, no recommendations, and why), the aggregation/latency behavior (one round trip vs five), and that body battery is returned at two distinct points (wake and most-recent) because they answer different questions. It does not address failure/partial-data behavior or whether a future date is rejected, which are the remaining gaps.

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?

The purpose and aggregation scope are front-loaded in the first sentence, and each subsequent sentence carries distinct information (dual body-battery reporting, deliberate absence of thresholds). The rationale about thresholds living in the coaching skill is slightly editorial but defensible as it explains an omission an agent might otherwise assume was a bug.

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 structure need not be re-described, and the description correctly focuses on what is aggregated and what is deliberately excluded. For a single-parameter read tool this is nearly complete; only edge behavior (missing source data, timezone handling for the date) is unaddressed.

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?

Schema description coverage is 0%, so the description must compensate, and it does supply the one thing missing: the required 'date' format (YYYY-MM-DD). It adds no timezone or date-range semantics, which matter for a 'morning' aggregate tied to wake time, so it falls short of fully compensating.

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 morning's measurements') and then enumerates exactly what is aggregated: sleep, recovery (body battery, HRV, resting HR), training readiness, and today's scheduled workout. This clearly distinguishes it from the five sibling tools it wraps (get_sleep_data, get_body_battery, get_training_readiness, get_scheduled_workouts), so an agent can tell it apart without opening a 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?

The 'five endpoints in one round trip' framing strongly implies when to prefer this over the individual siblings, and it explicitly bounds scope by noting no alerts and no recommendations are returned ('those thresholds live in the coaching skill'). It stops short of naming the alternative tools or stating 'use this instead of calling get_sleep_data + get_body_battery + ...', so usage is clear but not fully spelled out.

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