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

Annotations already declare a safe, idempotent, closed-world read, and the description goes well beyond them: it discloses exactly which conditions are flagged, that NMDP MAC codes are flagged rather than expanded, and that it resolves against a pinned release. The no-identifiers constraint is also stated behaviorally.

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 operations come first, then the structural example, then the constraints. The PII warning is repeated from the schema description, which is the one clause that does not fully earn its place, but overall the length is justified by the tool's complexity.

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 single-parameter tool with an output schema and rich annotations, the description covers scope, accepted inputs, flagging behavior, and the clinical-interpretation boundary. Given the output schema exists, no return-value explanation is needed.

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 baseline is 3, but the description adds real syntax information the schema lacks: accepted nomenclature eras, G/P group names, A*02:XX and two-field A*02:01g forms, the locus->allele map example, and that MAC codes are not expanded. That meaningfully reduces caller ambiguity.

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?

States a precise verb and resource: QC-check one HLA typing across all loci against the pinned release. The enumerated checks (resolution, locus mismatch, B-leader/KIR-ligand computation) make it unmistakably distinct from siblings like validate_gl_string and normalize_allele.

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?

Explicitly scopes usage with 'Nomenclature and internal-consistency checking of the report, not clinical interpretation,' which is a clear when-not boundary. However, it never names a sibling tool for the adjacent tasks (single-allele normalization, GL string validation), so routing among alternatives is left to the agent.

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