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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that outputs are predictions rather than measurements and that an applicability verdict should be checked, but it omits failure modes, permissions, output format, and what the verdict actually entails.

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 tightly written sentences with no filler. The core prediction task is front-loaded, and the critical caveat follows immediately.

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 3-parameter tool with no output schema and no annotations, the description names the predicted quantities and adds a key usage caveat. However, it leaves assay_type semantics unexplained and does not describe the return format or the applicability verdict, leaving clear gaps for correct invocation.

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 33% (only concentration has a description), so the description should compensate but does not. It only mentions 'from a SMILES' and adds no meaning for assay_type (microsomes vs hepatocytes) or concentration beyond what the schema already provides.

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?

Uses a specific verb ('Predict') and names the exact predicted quantities (fu,p, fu,inc) plus secondary outputs (human CL and Vss) from a SMILES. The purpose is clear and distinguishable from a generic prediction tool, but it does not explicitly contrast with siblings like target_clint or calc_clhep.

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?

No guidance is given on when to choose this tool over alternatives such as target_clint, scale_to_human, or calc_clhep. The caveat 'Predictions, not measurements; check the applicability verdict' implies an interpretation context but does not state conditions for use, exclusions, or sibling comparisons.

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