query_health

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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so safety is clear. The description adds useful behavioral context: 'Bounded cached detail' indicates a bounded and cached dataset, 'Missing buckets remain missing' discloses handling of gaps, and 'No arbitrary SQL' restricts query capability. It also explains the aggregation_minutes range. This goes beyond the annotations and covers key runtime behavior.

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 description is a single, dense paragraph that front-loads the core idea ('Bounded cached detail') and then presents usage rules in a structured, scannable way using semicolons and line breaks. Every sentence adds value: time semantics, defaults, limits, pagination, session selection, metric options, backend note, and aggregation range. No filler or redundancy.

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 9 parameters and an output schema present, the description covers the critical usage aspects: time ranges, limits, session selection, metric flexibility, aggregation bounds, and the caching caveat. It references a device profile for extended metrics. It does not explicitly explain timezone format or offset behavior, but given the mention of offset-aware ISO timestamps and the existence of an output schema, the description is sufficiently complete for safe invocation.

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. It does so by explaining start/end semantics (inclusive/exclusive, ISO timestamps, optional defaults), limit and pagination, metric examples ('heart_rate.bpm (default), steps, calories, distance'), and aggregation_minutes range. It mentions timezone indirectly via 'offset-aware ISO timestamps' but does not detail the timezone parameter or offset parameter. Overall, it adds substantial meaning beyond the raw schema.

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 'Bounded cached detail: metric buckets, sleep sessions, or workouts.' This clearly names the resource (bounded cached health data) and the specific data kinds, distinguishing it from live measurement tools like measure_heart_rate and daily summaries like get_daily_report. The verb 'query' is implied and the scope is explicit.

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 description gives explicit usage conditions: 'Supply both start (inclusive) and end (exclusive) as offset-aware ISO timestamps, or neither for the last 24 hours (timeseries) / 30 days (sessions).' It also explains pagination with 'limit 1..500; use returned pagination for more' and session selection via 'Session IDs from summaries.' It does not name specific alternatives but the conditions make the intended usage clear. A minor gap is not explicitly stating when not to use the tool, but it is effectively covered.

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