recovery_correlations

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

Beyond the read-only/idempotent annotations, the description discloses important behavior: the maximum 366-day window, pairing each day's training with the following night, inclusion of sample size and correlation strength, training-vs-rest and evening-vs-earlier comparisons, and handling of unrecorded Garmin fields. It also gives interpretive caveats that prevent causal or medical overclaiming.

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 description is dense but mostly front-loaded: it states the question, analysis window, pairing logic, and outputs before caveats. The leading 'I3.' label is unexplained and the caveat sentences lengthen it, but every sentence contributes useful information.

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 complex correlation tool with an output schema and safety annotations, the description is complete enough to call correctly. It covers the analytical purpose, time window, pairing logic, sport filtering, summary outputs, missing-data handling, and interpretation limits.

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 100%, so start, end, and activity_type are already well documented. The description adds a little context with 'up to 366 days' and 'Can focus on one sport,' but the schema provides more precise parameter semantics such as inclusive dates and excluding days with only other sports.

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 clearly states that this tool computes correlations between training and next-night sleep/HRV, with sample size, strength, and training-vs-rest averages. It distinguishes the analysis from raw sibling tools like get_sleep, get_hrv, and training_summary, though it opens with an unexplained label/question rather than a declarative verb-resource statement.

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 by the question 'Does training go with better or worse sleep and HRV?' and by the note that one sport can be focused on. However, it does not explicitly say when to choose this tool over get_sleep, get_hrv, trend, or compare_periods, nor does it state exclusions beyond the 366-day window.

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