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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuine value by disclosing the return shape (all applicable methods, each with a measured error) and the observed-vs-predicted input rule, but says nothing about how many methods exist, failure behavior, or whether results can be partially empty.

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 short sentences, front-loaded with the operation and its scope, followed by the input constraint. No filler and nothing the agent must re-read.

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 2-parameter, no-output-schema tool this is nearly complete: it names the species set, the input semantics, and the broad return content. The only gap is that fu_p_human and its role in the fu-corrected methods are left entirely to the schema.

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 100%, so the baseline is 3; the description earns an extra point by clarifying that the 'cl' values must be observed in-vivo measurements, never predicted or back-calculated — a semantic constraint the schema does not encode. It also implicitly enumerates the valid species.

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 concrete verb+resource: predict human plasma CL from observed animal in-vivo CL, enumerating the supported species (rat, dog, monkey) and noting it returns every applicable method with its measured error. That is clearly distinct from siblings like calc_clhep or target_clint, though it never names them explicitly to force the contrast.

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?

"Observed animal CL only, never predicted" is an explicit input-precondition that steers the agent away from misuse where sibling tools might be the right choice. It gives clear context for when this applies, but stops short of naming alternatives or stating when-not to call it.

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