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

Annotations already cover read-only, idempotent, non-destructive behavior, so the description does not need to restate those. It adds useful behavioral context beyond annotations: 'Every field carries its source page' is a provenance guarantee, and 'one pathway row per jurisdiction × pathway' clarifies output cardinality. These are meaningful disclosures an agent would not get from the schema or annotations.

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 a single dense sentence that front-loads the core scope ('One molecule') and then lists the record's contents efficiently. It has no redundant phrases and every clause adds information.

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?

The annotations and output schema reduce the burden on the description, and the description gives a solid overview of return contents and provenance. However, it lacks input-format guidance for the 'substance' parameter and any usage routing among the many get_* siblings, so the definition is only minimally complete for correct invocation.

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?

The schema has a single required parameter 'substance' with 0% description coverage, so the description must compensate. It does not clarify what values 'substance' accepts (e.g., INN, UNII, CAS, or a database identifier) or its format. The description lists identifiers as record fields, not as accepted inputs, leaving the agent to guess how to populate the required parameter.

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 clearly defines the tool's resource: a single substance record, enumerating its specific contents (identifiers, aliases, class, pathway rows, enforcement events, safety references). The phrase 'one molecule' and the distinct field set differentiate it from sibling tools like get_item and get_safety_label, even without naming them.

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 description gives no explicit guidance on when to use this tool instead of related siblings. It implies the tool is for fetching a single substance record, but it never states exclusions, alternatives, or conditions. An agent must infer usage from the tool name and content list.

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