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

Annotations only give readOnlyHint=false, destructiveHint=false, openWorldHint=true. The description goes well beyond that: it discloses the exact endpoint sequence, the 204 response, the read-back verification, the side effect that setting restingHeartRate disables restingHrAutoUpdateUsed, and the non-obvious domain rule that floors are not recomputed server-side.

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-loads the one-line purpose, then the mechanics in a compact, information-dense form with no filler. It is long, but nearly every clause carries behavior an agent must know; the truncation is the only real structural flaw.

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 mutating tool with a nested object payload, no output schema and no explicit annotation coverage, the description supplies the return behavior ('returns the profile READ BACK'), the side effect, and the server-side non-recomputation caveat. Only the truncated zone-floor validation rule keeps it from being fully self-sufficient.

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 nominally low, so the description carries the load: it enumerates the accepted payload fields, pins zoneFloors to '[5 bpm]', and explains the sport-default fallback. It adds real meaning over the bare nested object, though the final constraint sentence is truncated mid-word ('Floors must be stric…'), leaving part of the validation rule unstated.

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 and resource ('Changes one heart-rate zone profile') and adds scope ('one profile', not all). The GET/PUT flow makes it clearly distinguishable from the read-only sibling get_heart_rate_zones and from delete_heart_rate_zones without opening any schema.

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 procedural guidance an agent needs: it describes the read-modify-write sequence, notes that a sport without a profile starts from DEFAULT's, and instructs 'Send `zoneFloors` too' with the warning that Garmin does not recompute floors. It never explicitly names when to prefer this over delete_heart_rate_zones or the read tools, so it stops short of full alternative routing.

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