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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: the de-duplication rule (each sensor counted once per bucket), the 100-sensor cap, the UTC-day bucketing, and the 92-day-per-call limit for daily aggregation.

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 dense but purposeful sentences; the aggregation semantics are front-loaded and nothing is filler. The telegraphic style and the mid-sentence cross-reference to get_sensor_readings make it slightly harder to parse than it needs to be.

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 must carry return semantics, and it does indicate the response includes a per-bucket mean and a per-bucket sensor count. Gaps remain on the exact return shape (timestamps, ordering) and how sensors with no readings in a bucket are treated, which matters for a 100-sensor aggregate.

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 50%: to/from are documented in the schema, but ids and interval carry no schema descriptions. The description partially compensates by tying the 100-item cap to ids, enumerating the interval buckets (5min/hour/UTC day), and deferring window semantics to get_sensor_readings; it still does not explain from/to defaults or the interaction between range length and interval.

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 states a specific aggregation (mean) over a specific resource (a group of up to 100 sensors) at specific bucket granularities, and it clarifies the counting rule (each sensor once per bucket) plus the accompanying count of sensors per bucket. It is not a tautology of the title, though it is phrased as a noun phrase rather than a verb and only implicitly contrasts with get_sensor_readings via the window reference.

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 implies when it applies (you want aggregated means rather than raw readings) and points to get_sensor_readings for window semantics, and it gives one hard operating constraint (at most 92 days per call when interval is day). However, it never explicitly says when to choose this over get_sensor_readings or what happens for non-day intervals at long ranges.

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