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

With no annotations, the description carries the full behavioral burden. It adds valuable context that rows are not collapsed and that labels are returned so the caller can compare correctly, but it omits operational behavior such as whether the operation is read-only, how limit/pagination works, and what filtering does.

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?

The response shape is front-loaded in the first sentence, and the remaining sentences explain the non-collapsed behavior without excessive repetition. It is somewhat discursive, but the framing is purposeful and not bloated.

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 five-parameter tool with no output schema and no annotations, the description is incomplete. It explains the conceptual output granularity, but it leaves parameter meanings, filtering behavior, defaults, and return structure largely undocumented.

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 0% for five parameters, so the description needs to explain drug filtering, limit, metric, estimand, and timepoint_weeks. It only alludes conceptually to doses, timepoints, and estimands; it does not map any parameter to its meaning, accepted values, or default behavior.

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 clearly describes the returned resource: a weight-loss table joined to trial design with one row per arm and timepoint. It distinguishes this output from a collapsed per-drug comparison, so an agent can tell what it will get. It does not, however, differentiate itself from the named sibling tools.

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: the tool is for making efficacy comparisons while leaving the choice among doses, timepoints, and estimands to the caller. The description explains that it is not meant to pick a single winner per drug, but it does not give explicit when-to-use conditions or name alternatives among siblings.

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