List Apple Health Records

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

Adds substantial context beyond the annotations: the full-file scan cost model (~33 ms per MB, ~3 s for 84 MB), in-memory caching of identical queries, the fact that `limit` caps only the returned list and not the aggregate, and the nested `numeric` statistics shape. This far exceeds the bar set by readOnlyHint/idempotentHint and does not contradict them.

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?

Dense and front-loaded: purpose and the critical `limit` caveat come first, followed by cost and mode guidance. Slightly long, but every sentence carries operational weight — the COST block, caching note, and mode routing all earn their place.

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 tool with 7 parameters and no output schema, the description is thorough. It covers the return shape (truncated/limit_applied/matched_count and nested numeric stats), the cost model, caching, and mode behavior. Little an agent needs to call it correctly is missing.

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 only 57%, leaving limit, privacy_mode, and response_format undocumented in the schema. The description compensates by explaining `limit` semantics (caps the list only, not the aggregate), the three privacy modes and their behavior, and the aggregate block's nested structure. This is meaningful value added beyond the schema.

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 and resource: 'List bounded records from a local Apple Health export.xml.' It is distinguishable from siblings like apple_health_list_workouts (workouts only) and apple_health_daily_summary (aggregated view) by focusing on raw record listing with type/start/end filters. However, it never names a sibling explicitly, leaving the agent to infer the distinction.

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?

Offers explicit mode-selection guidance — 'For a cheap bounded page with no full-file scan, pass privacy_mode "structured" or "raw"' — and spells out the cost tradeoff of summary mode versus the cached repeat-query path. It does not explicitly exclude sibling tools (e.g., when to prefer list_workouts), so the alternative-routing guidance is intra-tool rather than cross-tool.

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