garmin_add_body_composition

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the write-and-safe profile is covered structurally. Beyond that, the description adds only the smart-scale analogy and says nothing about whether an existing measurement for the same time is overwritten, what the server does with omitted optional fields, or what a successful write returns.

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?

One short, front-loaded sentence with no wasted words. Its brevity is efficient, though it borders on under-specification for a 13-parameter mutation, so it is not a full 5.

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?

Incorrect scoring would be incomplete here; the tool has 13 parameters, 46% schema coverage, a mutation annotation profile, and no output schema. The single-sentence description leaves the agent without enough to fill the undocumented metrics correctly or to know how repeated writes at the same timestamp behave.

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 only 46% across 13 parameters, so the description is expected to compensate, and it does not: weight_kg is implied by the title but bmi, percent_fat, metabolic_age, physique_rating, and visceral_fat_rating are undocumented in both places, leaving units and expected ranges ambiguous. The only value added is the implicit signal that all metrics are optional except weight.

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 gives a specific verb and resource: 'Record a full body-composition measurement', with the analogy '(as a smart scale would)' clarifying that it is a multi-metric snapshot. It is clear on its own, but it never distinguishes itself from the sibling garmin_add_weigh_in or from garmin_body, so an agent must guess which entry path fits a simple weight-only log.

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?

There is no guidance on when to use this versus garmin_add_weigh_in or garmin_body, no prerequisites, and no statement about whether a measurement at an existing timestamp is replaced or duplicated. The parenthetical hints at bulk scale-style entry but does not route the agent anywhere.

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