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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds genuinely useful behavioral context: the returned value types (IC50/Ki/EC50, assay descriptions, units) and the notable edge case that a biologic returns an explanatory response rather than a bare empty list. This exceeds what annotations alone communicate.

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 description is two concise sentences with the core operation and return fields front-loaded. The second sentence earns its place by flagging a non-obvious open-world behavior. There is no redundancy or filler.

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 simple optional-filter retrieval tool, the description plus schema and annotations cover the data source, filters, returned value types, empty-result edge case, and safety profile. An output schema exists, so repeating return structure is unnecessary.

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%, so the description must compensate. It does clarify that molecule_chembl_id and target_chembl_id can be used together or separately via 'and/or'. It does not expand on the limit parameter or constraints, though the parameter names and schema examples are mostly self-explanatory.

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 opens with a precise verb and resource: 'Retrieve bioactivity records from ChEMBL filtered by molecule_chembl_id and/or target_chembl_id', and it names the concrete value types returned. It does not explicitly differentiate this from ChEMBL-related siblings like chembl_mechanism, molecule, or target, 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?

The filter options and the small-molecule scope imply when to use this tool: for ChEMBL bioactivity data keyed by molecule or target IDs. It also gives a useful exclusion by noting that biologics have no such data by construction. However, it never names sibling alternatives or states when to prefer chembl_mechanism, drug_indications, molecule, or target, leaving that comparison implicit.

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