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 fully covered and the description does not need to restate it. The description adds one piece of behavioral context, "RETURNS: 毒性风险分级" (graded toxicity risk), which is useful given there is no output schema. Beyond that it says nothing about the underlying model, how grades are defined, or whether endpoints are batched — hence a 3, not higher.

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 pipe-delimited layout is front-loaded and scannable, with USE WHEN placed before ALIASES. However, the alias block is largely padding — 毒性预测, hERG, DILI, toxicity and SMILES simply restate the title and the input, and the bilingual duplication of the title at the start consumes tokens without adding selection value.

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 two-parameter, read-only, closed-world tool with no output schema, an agent has enough to call it: what it predicts, what input it needs, and roughly what comes back. It is still missing the interpretation of the risk grades and any mention of the Ames endpoint exposed in the schema, which an agent would need to use results correctly.

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 both parameters are already documented (smiles = compound SMILES; endpoints = hERG/DILI/Ames). The description adds no meaning beyond the schema and never mentions the endpoints parameter or the Ames option at all. Baseline 3 applies when the schema carries the parameter burden.

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 a specific verb-and-resource pair: predicting cardiac (hERG) and liver (DILI) toxicity risk from a SMILES string. This is concrete enough to separate it from neighbors such as protein_physchem or drug_interaction_check. It does not explicitly contrast itself with the closest sibling, toxicology_assess, so it stops 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?

"USE WHEN: cardiac (hERG) and liver (DILI) toxicity risk from a SMILES string" gives an explicit trigger condition and required input. There is no when-not guidance and no named alternative (e.g., when to prefer toxicology_assess over this endpoint-level predictor), which is the only missing piece.

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