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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: the data is sourced from a specific calculator's curves, it is a trial-average rather than a per-person prediction, and the time horizons returned are 6, 12 and 18 months.

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?

Roughly two sentences, front-loaded with the core computation and followed by the essential caveat. Every clause earns its place and nothing is padded.

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?

With no output schema, the description carries the burden of describing returns; it does so adequately by naming the metric and the 6/12/18-month timepoints. A brief note on whether results are per-medication rows or a single curve for the supplied weight would close the remaining ambiguity.

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 50%: 'weight' is described as current body weight, while 'unit' carries only an enum and default with no prose. The description adds the notion of a 'starting weight' but does not clarify the unit parameter or how weight/unit interact, so it neither fully compensates for the gap nor is redundant.

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 computation (trial-averaged weight loss at 6/12/18 months for a given starting weight) rather than restating the name, so an agent knows exactly what question it answers. It does not, however, contrast itself against the obvious sibling compare_weight_loss_medications, and the phrase 'per medication' is slightly at odds with a schema that has no medication parameter.

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?

Usage is implied by 'the same curves as deer.supply/calculator,' which tells the agent this is a population-average estimator rather than a personalized forecast. There is no explicit when-to-use/when-not guidance and no pointer to compare_weight_loss_medications for the multi-drug case.

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