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

Annotations already declare readOnlyHint and idempotentHint, but the description adds meaningful behavioral context: it is a live query against LANL's keyless JSON API with no ingest, so results are always current. It also discloses the output shape (citation, keywords, HXB2 coordinates, and ab binding region/neutralizing classification) and a cross-parameter constraint not visible in 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 dense but not padded: every sentence contributes a distinct fact—scope, sibling distinction, example queries, live behavior, parameter roles, and return fields. The crucial distinction is front-loaded before parameter details, and the format is easy for an agent to scan.

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 tool with 5 parameters, no output schema, and a close sibling, the description covers all essential context: what it searches, which table values do what, the at-least-one query requirement, return fields, and live freshness. Nothing an agent needs to decide whether to invoke it or interpret results 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 value by explaining table enum semantics, restricting mab_name to the 'ab' table, and explicitly stating 'At least one of mab_name, epitope, protein_name is required' — a non-obvious constraint not captured by the schema's required list. It does not discuss limit, but the schema already documents that parameter fully.

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 specific verb and resource ('Search the LANL HIV Molecular Immunology Database') and immediately enumerates the three response types: CTL/CD8+, T-helper/CD4+, and antibody binding sites. It even provides concrete example questions and explicitly contrasts itself with catnap_search_neutralization, making the tool's function fully unambiguous.

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 explicitly names the closest sibling (catnap_search_neutralization) and explains when THIS tool is appropriate ('WHERE on the virus an immune response targets and WHICH HLA restricts it') versus when it is not ('not how potently an antibody neutralizes'). It also states the live/no-ingest property and the required parameter combination, leaving little room for selection error.

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