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

With no annotations, the description carries the full burden, and it does disclose the crucial behavioral trait that results are reference text only and 'not a verification and not a verdict' — useful framing that prevents over-trust. It omits read-only/mutation status, result limits, ranking or pagination behavior, and what an empty result means.

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?

Roughly two-thirds of the text is repeated safety boilerplate ('Not for clinical use', 'testing and evaluation only', 'Do not use its results to diagnose, treat, prescribe', 'not a verification and not a verdict'), which buries the actual capability at the end. The disclaimer is defensible but is stated three times in different words rather than once, up front or after the purpose.

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?

An output schema exists, so return values need not be explained, and the description adequately covers what the tool searches. For a 3-parameter, all-optional search tool, though, the combination semantics and the no-parameter behavior are genuinely missing and would change how an agent calls it.

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 coverage is 0%, so the description must compensate, and it partially does by specifying match semantics: 'exact ingredient name', 'exact category name', but 'words in the title' for title_contains. It never addresses the three optional parameters' interaction — whether multiple filters are ANDed, and what happens if none are supplied.

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 operative sentence names a specific verb and resource: 'Find FDA over-the-counter (OTC) drug monographs', and it enumerates the three lookup keys (ingredient, category, title words). It does not, however, differentiate itself from near siblings such as find_fda_label, get_otc_monograph, or read_otc_monograph_section, so an agent must infer that this is the discovery/search step rather than the retrieval step.

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 only 'when' guidance is a safety constraint ('Not for clinical use', 'Use synthetic test data only'), which is about admissibility, not tool selection. Nothing states when to call this versus get_otc_monograph (fetch a specific one) or find_fda_label (the Rx-label sibling), which is exactly the choice an agent faces in this toolset.

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