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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered by structured data. The description adds the return payload in concept ('RETURNS: 毒性风险分级') and the assessed domains, but says nothing about the scoring model, assumptions, or what inputs drive the grading. Credit is modest because the annotation block carries the operational burden.

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?

Pipe-delimited sections front-load the 'USE WHEN' trigger ahead of aliases, so the most useful content appears first. The ALIASES block partially duplicates the bilingual title, which is minor template overhead rather than real waste.

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 4-parameter, single-required-input assessment tool with no output schema, the definition states what comes back only as a label ('toxicity risk grading') without any structure or interpretation guidance. The required-input expectation lives entirely in the schema. Adequate to select and call, but thin on what the agent should expect to do with the result.

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%, and the schema itself flags hERG_IC50_nM as required and the cardiac-toxicity core input. The description adds no parameter-level meaning beyond that, so baseline 3 applies; there is no guidance on how logP, daily_dose_mg, or expected_Cmax_nM interact with the risk grade.

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 the resource (nonclinical toxicology assessment) and the specific risk domains it covers: hERG, DILI, genotoxicity, and an overall risk level. That is enough for an agent to tell it apart from pk_pd_assess or animal_dose_volume. The verb is implicit rather than a crisp action verb, which keeps it short of a 5.

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?

The explicit 'USE WHEN: nonclinical toxicology risk' clause gives a clear triggering context with concrete sub-cases (hERG / DILI / genotoxicity). It does not name when NOT to use it or point to a sibling alternative, so routing among the PK/tox family is left to inference.

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