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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond that: Travel Day is context-only and can coexist with training, meaning a rest-day entry does not imply absence of training, and it explicitly instructs the agent to infer default dates rather than prompt the user.

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?

Purpose is front-loaded in the first sentence, followed by usage rationale and then a short inference directive. Every sentence carries information, though the INFER block restates defaults that the schema already declares, which is mildly redundant.

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?

An output schema exists, so return values do not need explaining, and annotations plus the output schema cover the safety and shape of results. The description supplies the interpretive context an agent needs (what a rest-day entry means, how it interacts with training data). It could be slightly stronger by noting the distinction from log_rest_day/cancel_rest_day, but it is complete enough to call correctly.

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 both parameters (start_date, end_date) are already fully documented with format and defaults. The description's 'default to 30 days ago / today' merely duplicates the schema defaults, and the INFER instruction is a call-behavior hint rather than added parameter semantics. Baseline 3 is appropriate.

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 verb (List) and a precise resource (user-selected Rest Day, Sick Day, and Travel Day context) with an explicit scope (within a date range). The semantic content — 'context-only, can coexist with training' — lets an agent distinguish it from data-bearing siblings like list_wellbeing or list_recovery_sessions without opening a schema.

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 clearly states when to reach for this tool: to explain a date with no workout or anomalous recovery/sleep/nutrition data. That is a real usage signal rather than restated purpose. It stops short of naming an alternative or a when-not condition (e.g., use list_personal_context for other context types, or log_rest_day to add one).

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