oura_resilience

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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds the default-date behavior and the specific output structure (level + contributors), which are useful context not captured in annotations. However, it does not mention any potential pitfalls (e.g., data availability for past dates) or response limitations, so it stays at an adequate but not rich level.

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 extremely concise: one purpose sentence plus a clearly formatted Args block. It front-loads the core functionality and parameter details with zero redundancy. Every sentence carries essential information, and the structure makes it easy to parse for an agent.

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 tool with one optional date parameter, read-only semantics, and an output schema present, the description is nearly complete. It covers the purpose, the specific data returned (level and contributors), and the parameter format/default. It does not describe error cases or edge scenarios, but given the tool's simplicity and the presence of an output schema, those are not critical gaps.

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 only parameter 'date' is undefined in the input schema (coverage 0%). The description compensates by stating the expected format 'YYYY-MM-DD' and the default behavior 'defaults to today', which are essential for correct invocation. It also clarifies that the tool returns data for a single date, aligning the parameter with the purpose. This goes beyond the bare type definition and is sufficient for an optional parameter.

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 states a specific action ('Get the long-term resilience level'), identifies the resource ('for a date'), and enumerates the expected outcome categories (limited/adequate/solid/strong/exceptional) and the components (sleep recovery, daytime recovery, stress). This clearly distinguishes it from siblings like oura_sleep or oura_stress by focusing on a composite resilience metric.

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 provides no guidance on when to use this tool versus alternatives. It does not mention scenarios where resilience is more appropriate than sleep, stress, or readiness, nor does it reference the sibling tools. The only usage cue is 'for a date', which is generic. The exact trigger conditions are left entirely to the agent to infer.

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