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

Annotations already cover the safety profile (readOnly, idempotent, destructive=false), yet the description adds substantial context beyond them: input normalization rules (salt forms merged, brand names not matched), the coverage level scale, and the crucial caveat that found:false is NOT a safety answer. This is exactly the extra behavioral context an agent needs.

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?

Dense but front-loaded: the core action and input rules come first, coverage matrix and the found:false caveat follow. Every sentence earns its place, though the single ~130-word block is slightly cramped and would benefit from light structuring.

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?

There is no output schema, so the description carries the return burden and does so fully, enumerating the verdict fields (found, severity, direction, summary, recommendation, recorded_for, evidence_level, sources) and the coverage scale. For a 2-param pairwise lookup, nothing material is 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 coverage is 100% so the baseline is 3, but the description adds real meaning: it clarifies that each param is a supplement (name or canonical_id) OR a medication (generic name), and notes that salt forms are merged while brand names are not matched. That disambiguation is present in neither schema field.

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+resource ('Point check of one pair') and scopes it precisely with input types and a size estimate (~1-3 KB). The 'one pair' framing implicitly distinguishes it from the listing sibling get_supplement_interactions, but it never names that sibling, so the differentiation is left to inference.

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 gives clear when-to-use boundaries: supplement+supplement uses curated data, supplement+medication uses FDA labels only, and medication+medication is explicitly not covered (no_match). It also directs 'Check status first' and explains what needs_confirmation/no_match mean for retry. It does not name the alternative tool for bulk interaction listing.

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