get_recovery_trends

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description adds the useful behavioral detail that results include flagging of markers that have drifted outside their usual range (resting HR up, HRV down, short sleep, load jump). It says nothing about caching, latency or data freshness, so it stops short of a 5.

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 main statement comes first, then the returned-metric list, then routing guidance, then the arg note — a sensible front-loaded order. It is a few lines longer than strictly necessary, with the metric enumeration and the get_plan coda partially overlapping in purpose, but no sentence is filler.

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 single-optional-parameter read tool with an output schema and read-only annotations, an agent has everything needed: what window it covers, what it returns conceptually, which questions it answers, and which siblings to use instead. The return-value enumeration is arguably redundant with the output schema but costs little.

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 has to carry the parameter, and it does: 'weeks: Weeks to look back, including this one (1-12). Defaults to 4.' It adds a hard range constraint and clarifies that the current partial week counts, neither of which is in the schema (which only shows type integer and default 4).

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 opening line names the resource and the scope precisely ('how the user is recovering across weeks, beside the training that caused it') and then enumerates the concrete metrics returned (HRV, resting HR, sleep, Body Battery, load). It explicitly differentiates itself from two siblings: get_readiness for today's training decision and get_plan for general training status.

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 supplies three verbatim user questions that should route here ('am I recovering well', 'is this block too much', 'why do I feel flat'), states the condition that selects a sibling instead ('For whether to train hard today, get_readiness is the one'), and positions itself relative to get_plan as a follow-on call rather than a starting point.

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