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

Annotations already establish idempotent=true, destructive=false, and readOnly=false, but the description adds substantive context beyond them: the response contains an Undo affordance and the recorded value feeds a smoothed trend rather than a single reading. It doesn't describe the shape of the returned payload, but an output schema exists to cover that.

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?

Four short sentences, front-loaded with the trigger, then the payload, the default, the downstream effect, and the exclusion. No sentence is 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 mutation tool with an output schema and solid annotations, the description supplies trigger, default semantics, downstream interpretation, and undo support — enough to call it correctly. The only thin spot is retry/idempotency behavior in prose, which the schema property already explains.

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 only 25% — just the idempotencyKey is documented — so the description has to carry the rest, and it does: it explains that weight and unit go together and that the timestamp defaults to now when null ('when (null is now)'). The numeric bounds and unit enum are left entirely to the schema, which limits it below a 5.

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 names a specific verb and resource combination ('when the person tells you their weight' + 'Give the weight and unit') and explicitly separates it from a look-alike task with 'Do not use to set a weight goal.' An agent can identify the tool without examining the 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?

The trigger condition ('when the person tells you their weight') and the exclusion ('Do not use to set a weight goal') are both stated outright. This is unambiguous routing guidance with no inference required.

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