health_get_spo2

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

No annotations are provided, so the description bears full responsibility. It thoroughly discloses caching behavior, the need for health_sync, data sparsity, the meaning of different bounds (min/max vs avg_ci), warning against comparing across them, and normal ranges. It also explains the live flag's effect. This is rich behavioral context.

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 with a clear overview, cache behavior, parameter explanations, return details, and clinical reference. Each sentence is purposeful, no fluff. Front-loaded with the main purpose.

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 (cache vs live, two bound types, overlap scenario), the description covers all important behaviors. It explains parameters, return values, caveats about bounds, and clinical context. With no annotations and sparse schema (no descriptions), it fully compensates, and the output schema is not provided but the description explains the return structure sufficiently.

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?

The schema has 3 parameters but their descriptions in the schema are minimal (only types and defaults). The description explains date formats (YYYY-MM-DD, YYYY-MM, or 30d), the meaning of 'live', and default ranges header. Since schema coverage is 0%, the description compensates well. It does not explain 'end_date' format explicitly but says it's YYYY-MM-DD. This adds significant value beyond 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?

The description clearly states it retrieves nightly SpO2 data with specific details about data source (local cache), and distinguishes itself from sibling health tools (e.g., health_get_heart_rate, health_get_sleep) by naming the metric and behavior. It also mentions the need for health_sync, differentiating its pipeline.

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 explicitly states to run health_sync first to populate the cache and explains when data is sparse (only on-wrist sleep tracking). It also explains the live parameter for re-fetching. However, it does not directly contrast with siblings or state when not to use this tool, though the resource is clear enough.

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