log_sleep

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

The description surfaces behaviors not visible from annotations: repeated calls on the same date upsert rather than duplicate, entries are always tagged manual, and wearable-provider sources are reserved for auto-sync. It also discloses the proactive questioning behavior. These details match the write-oriented annotations and add real operational transparency.

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 organized into labeled sections, each earning its place: core purpose, proactive collection, inference rule, subset/upsert behavior, and manual tagging. There is no redundant or filler content, and critical scoping information is front-loaded.

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 9-parameter write tool with many optional fields, the description answers the key operational questions: when to call it, what to ask if data is missing, how to compute date, whether partial data is allowed, what happens on duplicate calls, and how entries are tagged. An output schema also exists, so the description does not need to explain return values.

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 100%, so the schema already defines each parameter. The description adds valuable semantics by clarifying that date refers to the wake date (night ending on that date), defaults to today, allows any subset of fields, and that a second call on the same date updates the existing row. This goes beyond the schema's per-field descriptions.

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 opens with a specific verb-resource pair, 'Log a sleep entry', and lists the exact data types accepted (duration, score, stage breakdown, bedtime, wake time) and the sources (Fitbit, Oura, Whoop, Apple Health, manual recall). It clearly distinguishes this write tool from read siblings like list_sleep and show_sleep_detail, and separates manual entry from wearable auto-sync behavior.

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?

'Use when the user shares sleep data...' gives an explicit triggering condition. Proactive data collection instructions specify what to ask when the user wants to log but has no numbers, and the 'INFER — do not ask' section prevents unnecessary clarification. It does not explicitly name sibling alternatives for when to use something else, but the manual-vs-auto-sync note provides a meaningful exclusion rule.

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