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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description goes beyond these by adding crucial behavioral semantics: every value carries citation and PubMed id, and censored values ('>10') are returned as numeric_value null with censored true, never as the literal number. This is exactly the kind of edge-case behavior an agent needs and is not present in structured fields.

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?

Despite being longer than a two-liner, every sentence is load-bearing: purpose, example queries, data provenance, censoring semantics, usage guidance, and the sibling alternative. It is front-loaded with the functional purpose and contains zero 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 read-only lookup with no output schema and clear annotations, the description covers the source, the query flexibility, the special return semantics, and the alternative tool. Nothing an agent needs to call it correctly is missing, and the behavior is fully disclosed.

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%, so the baseline is 3. The description adds the combinatorial guidance 'Pass antibody, virus, or both' and concrete example values, but it does not explain parameter semantics beyond what the schema already provides. It earns the baseline but not more.

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 pair: potency measurements from LANL CATNAP, covers the two query directions (antibody across strains, strain across antibodies), and provides concrete example questions. It explicitly distinguishes itself from immunology_search by contrasting neutralization potency with binding, making it clearly differentiated from a close sibling.

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 explicitly says when to use the tool ('Pass antibody, virus, or both') and gives an explicit alternative with a condition: 'For where an immune response BINDS rather than how strongly it neutralizes, use immunology_search.' This leaves no ambiguity about the call boundary.

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