Apple Health Data Inventory

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds behavioral context: it scans a local export once, reports freshness and safe next calls, implying stateful behavior despite idempotency. No contradictions.

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?

Single sentence of 20 words, front-loaded with action ('Scan the local Apple Health export once'), no redundant words, every part adds value.

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?

The description lists all key outputs (record types, workouts, date coverage, freshness, safe next calls) and hints at the one-time nature. No output schema exists, but description adequately sets expectations. Could mention the response_format parameter briefly, but not essential.

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 60%, so baseline is 3. The description adds no parameter-specific details beyond what the schema already provides (start/end/timezone have descriptions). Parameters with enums are not elaborated in description.

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?

Description explicitly states the action ('Scan the local Apple Health export once and report...') and lists specific outputs (record types, workouts, date coverage, freshness, safe next calls). Clearly distinguishes from siblings like apple_health_list_records or apple_health_list_workouts.

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?

Description notes the tool is for a one-time initial scan and mentions it provides 'safe next calls,' guiding subsequent actions. While it doesn't explicitly exclude alternatives or state when not to use, the context is clear given the sibling tools.

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