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

Annotations already cover read-only, idempotent, non-destructive, closed-world, so the safety profile is settled. The description adds real behavioral context beyond them: the default 14-day window, the 180-day cap, and 'Siempre es una consulta completa' implying no pagination and full result sets regardless of size.

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 sentences, front-loaded with the period semantics, then a compact enumeration of returned metrics and a closing note on completeness. No filler, redundancy, or repeated schema content.

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 carries the burden of describing returns and does so by listing the specific aggregates produced. Combined with default/max window semantics, an agent has everything needed to call it correctly and anticipate the response shape.

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 coverage is 100%, so from/to formats are already documented. The description adds meaning the schema lacks: the default period when omitted (last 14 days) and the maximum span of 180 days, which directly affects how an agent chooses the arguments.

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 names a specific resource (glucose statistics for a period) and enumerates concrete outputs: time in range and per band, mean, variability, episodes, and breakdowns by time of day and weekday/weekend. This clearly sets it apart from raw-reading siblings like get_glucose or get_entries, though no sibling is named explicitly.

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?

It states the default window (last 14 days) and the maximum (180 days), which frames how to call it, but offers no explicit when-to-use vs when-not guidance or direction to an alternative tool for raw data. Usage must be inferred from the output enumeration.

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