get_trends

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

Annotations already declare readOnlyHint and openWorldHint=false, so safety is covered. The description adds genuinely useful behavior: unknown metric names return the full list, the default window, the 366-day cap, and that today is the default end. It still omits return shape details beyond 'baseline/band' and any rate or permission notes.

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?

Dense and front-loaded: the output shape leads, then the acceptable values, then windowing rules. The long metric enumeration is necessary given the absent enum in the schema; little is wasted, though the run-on windowing sentence is slightly hard to parse.

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 4-param read tool with no output schema, the description supplies the enumerable value sets, windowing semantics, and default behavior an agent needs. The main shortfall is that the return structure is only gestured at ('baseline/band'), with no explanation of fields.

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 0%, so the description must carry the load, and it largely does: it lists valid metric and score names, explains days=N vs start exclusivity, sets end's default, and states the default 30-day and max 366 windows. The only gap is the date string format for start/end.

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 output shape ('Daily series with baseline/band') and enumerates the metrics and score families it covers (rhr, hrv_7d, score:recovery, etc.). Clear what it does, but it never names or contrasts with sibling readers like get_sleep, get_activity, or get_overview, so differentiation is left to inference.

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?

Usage is implied through the parameter guidance ('Default last 30 days; max 366', 'days=N ... not with start'), which tells the agent how to scope a query but not when this tool beats get_overview or get_sleep. No explicit when-not or alternative routing.

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