health_sync

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It thoroughly explains that the tool fetches from the Google Health API and stores in SQLite, syncs incrementally based on the latest cache entry, and that since/until will re-fetch and upsert a specific window. These are meaningful behavioral traits beyond a simple 'sync' label, and the description is transparent about the side effects (writes to cache) and edge cases (backfill, gap repair, ignoring 'days' on subsequent syncs).

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 well-structured and front-loaded. It leads with the core purpose, then usage context, then parameter details, and closes with return value and alternative tools. Every sentence provides necessary information, and the parameter docs are formatted clearly. No filler or redundancy.

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?

Given the tool's complexity (4 parameters with nuanced behavior, incremental sync, backfill, window repair) and the presence of an output schema, the description is complete. It covers prerequisites, return summary, parameter semantics, and explicitly states what the tool is not for. It leaves no significant gaps for an agent to invoke it 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 0%, so the description must compensate. It does so comprehensively: data_types lists all acceptable values, comma-separated usage, and default; days explains its role for first sync and that it is ignored later; since and until describe their backfill and repair semantics, including that until requires since and that together they re-fetch exactly the specified window. This adds rich meaning beyond the bare schema definitions.

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 'Sync health data to the local cache,' which clearly identifies the verb (sync) and resource (health data to local cache). It further distinguishes itself from sibling tools by stating 'Run this before using other health_get_* tools' and 'Not for querying data - use health_get_heart_rate ... instead.' This makes the purpose unambiguous and differentiates it from the many read-only getter tools.

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?

The description gives explicit usage guidance: it should be run before using other health_get_* tools to populate the cache, and it is not for querying data. It also explains the incremental sync behavior and when to use since/until for backfill or gap repair, providing clear context for when to invoke this tool versus alternatives.

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