get_spo2

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

Annotations only declare readOnlyHint and openWorldHint; the description goes further by enumerating exactly what values come back and by warning that include_samples produces a large payload, which is a real cost signal for an agent batching calls. With no output schema, this return-shape disclosure carries meaningful weight beyond the annotations.

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?

Two short sentences, aggregate payload front-loaded ahead of the opt-in expensive flag. No filler, no restating of the tool name.

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 two-parameter read-only metric tool with no output schema, this covers return values and the sample-size tradeoff well. The only real gap is the date parameter's accepted format and default behavior when null.

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 0%, so both parameters lean on the description. include_samples is fully explained (boolean enabling individual and hourly readings, with a size caveat), but the date parameter is only implied by 'one day's' — no format (ISO vs YYYY-MM-DD), no behavior when omitted despite defaulting to null.

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 (get) and resource (one day's blood oxygen) plus the four aggregates returned (average, lowest, sleep average, 7-day average). It is clearly distinct from the other metric-specific siblings (get_steps, get_stress, get_hrv), though it never explicitly contrasts itself with any of them.

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 second sentence implies the default should be the aggregate view and that include_samples is an opt-in for detailed data, which is useful implicit routing within the tool. There is no statement of when to prefer a different sibling or when this data is unavailable, so guidance stops at implied.

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