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

Annotations already cover safety (readOnlyHint false, destructiveHint false, openWorldHint false), so the bar is lower. The description still adds real value beyond them: the non-editing guarantee and the ambiguity-abort behavior, which is a non-obvious transactional trait. It omits whether the creation is atomic across multiple exercise blocks beyond the name-match case.

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?

Front-loaded with purpose and the key constraint before any parameter detail. The example is lengthy but earns its place because the exercises array is untyped in the schema; the prose itself has no filler.

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 write tool with an output schema available, the description covers everything needed to call it correctly: purpose, non-editing guarantee, every parameter including the undocumented nested structure, and the ambiguity failure path.

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%, and the description fully compensates: it names all three parameters, spells out the nested exercise object's fields with defaults (sets 3, reps 10, rest_seconds 90), documents the optional weight_kg, and provides a concrete example the schema's untyped array cannot convey.

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 and location ('Create a new strength workout in the user's Garmin workout library') and explicitly separates itself from editing via 'It never edits an existing one'. It does not, however, distinguish itself from the sibling create_workout, which an agent must choose between.

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 clear usage context: creation-only, and a stated failure mode (ambiguous catalogue name → candidates returned, nothing created). It implies rather than states the alternative for modifying an existing workout (update_workout), and says nothing about the generic create_workout sibling.

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