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

Goes well beyond the readOnly/idempotent annotations: it discloses the 400-point cap, the 48-hour maximum window, that missing readings remain unknown (never zero/interpolated), and that time alignment is correlation only, not causation. These are non-obvious behavioral traits an agent could not infer from structured fields.

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?

Dense but front-loaded with the purpose first, then constraints, then caveats. Most sentences carry distinct, actionable information, though it is longer and more packed than strictly necessary for scannability.

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?

An output schema exists so return structure needn't be restated, yet the description still covers the point cap. Given the tool's moderate complexity and workout-alignment logic, the definition supplies everything needed 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 coverage is 100%, so baseline is 3, but the description adds value the schema lacks: the 48-hour maximum bound, the instruction not to guess workout timestamps, and how workout_id derives the range. It slightly exceeds the schema-only baseline.

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+resource: reading 'actually measured, timestamped blood glucose readings' from named sources (Health Connect, Ultrahuman). It explicitly differentiates from the sibling lab-results tools by noting lab tests belong elsewhere.

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?

Gives explicit use cases (intraday patterns, before/during/after-workout comparisons) and a clear decision rule between workout_id alignment vs a bounded timestamp range. It also names the alternative destination for lab tests, so routing is unambiguous.

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