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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior. The description adds genuinely useful context beyond them: results are predictions with an applicability verdict the caller must check, and CL/Vss are lower-confidence secondary outputs. It stops short of saying what the verdict contains or what happens when it fails.

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?

Two sentences with no filler, front-loading the primary outputs before the caveats. Every clause (secondary CL/Vss, prediction-vs-measurement, applicability verdict) carries distinct information.

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 usefully enumerates the returned quantities and the applicability verdict, and annotations cover the safety profile. The main remaining gap is that the verdict's meaning and the handling of a failed applicability check are left unspecified.

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 100%, so smiles, assay_type, and concentration are fully documented in the schema, including units and defaults. The description only repeats SMILES as input and does not clarify the assay_type/concentration interaction beyond what the schema already says. Baseline 3 applies.

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 (Predict) and precise resources (fu,p and fu,inc from a SMILES, plus secondary structure-only human CL and Vss). The named outputs distinguish it from siblings like calc_clhep, but no sibling is explicitly named or ruled out.

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?

"Predictions, not measurements" and "check the applicability verdict" imply a structure-only early-screening use case, and the CL/Vss are flagged as "second opinions." However, no explicit when-to-use/when-not-to-use conditions or named alternatives (e.g. calc_clhep, scale_to_human) are given.

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