health_get_exercises

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

No annotations are provided, so the description carries the full burden. It explicitly states the default behavior is reading from a local cache, that live=True triggers an API re-fetch, and it mentions a specific data-quality caveat ('HR data from cycling may be unreliable'). This is strong behavioral disclosure.

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 opening sentence, a behavior note, and a clean Args section. It is concise enough and front-loaded. The only minor deduction is for the 'Returns' section listing fields, which could be slightly trimmed since an output schema exists, but it remains useful for clarity.

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 optional parameters, no annotations, 0% schema coverage), the description is thoroughly complete. It covers defaults, parameter semantics, behavioral nuances, and return value composition. The output schema exists but the text description of return fields provides additional clarity.

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 significantly. It does: it explains the date format options ('YYYY-MM-DD', 'YYYY-MM', or '30d'), describes exercise_type as a case-insensitive substring filter, and clarifies what live does. This adds substantial meaning beyond the schema's bare type definitions. The only minor gap is not explaining the default of start_date precisely.

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 the tool's purpose: 'Get exercise log entries (individual tracked activities)'. It uses a specific verb+resource construction and immediately distinguishes it from sibling health_get_* tools by focusing on 'exercise' as opposed to heart rate, sleep, weight, etc. The phrase 'individual tracked activities' adds precision.

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 explicitly instructs to run health_sync first to populate the cache, and it indicates when to use live=True to fetch from the API. This provides clear context on when to use this tool versus the synchronization tool.

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