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

Annotations already establish that this is a safe, read-only, idempotent lookup, and the description adds meaningful return context: each neighbour includes measured human plasma CL and predicted CL from measured inputs. It also explicitly bounds behavior by stating that it returns neighbours only, not a prediction for the query.

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 definition is three tight sentences, front-loaded with what the tool returns and immediately followed by its intended diagnostic use. Every sentence carries useful information, including the limitation that this is not a prediction.

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 small read-only lookup with full parameter schema coverage and no output schema, the description supplies the return format and the interpretation rule an agent needs. Nothing relevant to selecting or using the tool correctly appears to be missing.

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%, with both 'smiles' and 'n' documented directly in the schema. The description reinforces that the query is a SMILES and that results are nearest neighbours, but it adds no extra parameter semantics beyond what the schema already provides, so baseline 3 is appropriate.

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 states a specific verb and resource: it returns nearest reference drugs to a SMILES, using Tanimoto similarity with Morgan radius 2. It also clearly distinguishes itself from calc_clhep by framing itself as a trust-check on that prediction tool rather than a predictor.

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?

It explicitly says when to use it: to judge how far to trust calc_clhep for a chemotype, with the decision rule 'if IVIVE missed on the neighbours, expect it to miss here.' This is a direct usage relationship to the sibling tool rather than implied guidance.

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