get_usage_categories

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

With no annotations present, the description carries the full disclosure burden. It does add meaningful behavioral context—the profile_pid fallback to a 'configured profile_pid' and the semantics of day ('0 = today') and ndays. However, it remains silent on output volume, error conditions, or data freshness, which a read tool could disclose.

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 content is efficiently structured: a single one-sentence opener followed by a scannable Args list with consistent 'name: meaning' lines. It front-loads the core purpose and wastes no words, with only the slightly awkward 'Days ago to start' phrasing preventing a 5.

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?

For a read-only tool with a non-trivial date-window semantics and an external profile dependency, the description provides the essential contract: source of profile ID, window start, and window length. The only gap is the lack of a return-value sketch, but that's a minor omission for a category-breakdown tool.

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?

Since schema description coverage is 0%, the description fully shoulders the documentation load by explaining all three parameters with provenance (profile_pid from list_profiles) and units (days ago, window size). This is a strong compensation for an empty schema, though the parameter meanings could have been more richly detailed (e.g., timezone handling for 'today').

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 uses a specific verb+resource ('Get internet usage broken down by category') with concrete examples (games, social, video). It's clear this returns categorized usage per profile, which conveys the tool's differentiating function, though it never explicitly contrasts itself with the sibling get_usage.

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 intended use is implied well by context—get category-level usage rather than totals—and the docs point the agent to list_profiles for the profile_pid, establishing an implicit dependency. However, there is no explicit when-to-use guidance or mention of alternatives (e.g., get_usage for aggregate totals), leaving the routing decision to inference.

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