Today

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered and the description's burden is lower. It adds useful behavioural context by noting the response includes 'how fresh the data is' (staleness/sync awareness), but says nothing about what happens when no record exists for the requested date, or how heavy/latency-prone a full snapshot call is.

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 first sentence is a long comma-spliced inventory of metrics that front-loads payload contents instead of the tool's purpose, and includes redundant framing ('last night in detail'). Every item is arguably informative, but the structure buries the key operating instruction ('Pass a date for a past day') at the end.

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 one optional parameter, no output schema and annotations present, the description does the heavy lifting on return contents and is therefore reasonably complete for calling the tool correctly. The remaining gap is selection guidance against the many overlapping report siblings, which is the main thing an agent would still get wrong.

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 0%, so the description must carry the parameter, and it does: 'Pass a date for a past day' establishes that date is optional, defaults to today, and selects a historical day, which the bare pattern '^\\d{4}-\\d{2}-\\d{2}$' does not convey. It stops short of restating the expected YYYY-MM-DD format or any bounds on how far back dates are accepted.

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 enumerates the concrete payload (recovery status with green/amber/red, HRV, resting HR, sleep, training load, Body Battery, steps, weight trend, fitness age, latest run, data freshness), so an agent knows this is an all-in-one daily snapshot rather than a narrow report. It lacks an explicit verb phrase and never distinguishes itself from siblings like get_body_report, get_sleep_stress_report or get_weekly_summary, which overlap heavily with the listed contents.

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 only guidance is the closing sentence 'Pass a date for a past day', which clarifies default behaviour but not tool selection. There is no statement of when to pick this over get_weekly_summary, get_body_report, or get_sleep_stress_report, nor any prerequisite or exclusion, leaving the agent to guess among near-duplicate siblings.

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