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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so the description is free to add context. It does: it explains the tool resolves alleles, flags issues, computes profiles, and accepts any nomenclature era. It also emphasizes no patient identifiers. This adds substantial behavioral guidance beyond the annotations, without contradiction.

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 long but information-dense, with every sentence contributing. It is front-loaded with the primary purpose and checks, then provides input format and constraints. The structure is logical and avoids fluff, though it could be tightened slightly without losing meaning.

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?

Given a single well-documented parameter, an existing output schema, and rich annotations, the description covers the tool's purpose, checks, input format, and limitations. It lacks an explicit note about whether all loci are required or how errors are reported, but these are minor given the output schema and the clear purpose. It is nearly complete for an agent to call it correctly.

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?

The schema description coverage is 100% and already describes the parameter (typing object with allele strings only, no identifiers). The tool description adds value by specifying 'up to 4 reported allele names', 'any nomenclature era', and that it is a full typing across loci. These details are not present in the schema, enhancing semantic understanding.

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 very specific verb ('QC-check') and resource ('one HLA typing (all loci) against the pinned release'), then enumerates the exact checks (resolves alleles, flags unresolvable/outdated/locus-mismatched/null, flags too-many/single/homozygous, computes B-leader and KIR-ligand profiles, DRB3/4/5 expected-vs-reported). This clearly distinguishes it from siblings like validate_gl_string or normalize_allele, and even clarifies it is not clinical interpretation.

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 implies usage context (QC of a complete typing, not a single allele) and states what it is NOT (clinical interpretation). However, it does not explicitly name alternative tools or conditions for selecting this over siblings, leaving the 'when-to-use' slightly implicit rather than directly contrasted.

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