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

With no annotations at all, the description carries the full behavioral burden and does disclose meaningful traits: practice reports score immediately slot by slot, while hidden reports stay pending until a DIFFERENT teammate vets them via hla_vet. That self-vetting restriction is exactly the kind of constraint an agent cannot get from schema. What is missing is the response shape, what happens on a bad api_key or malformed answer, and whether submissions can be retried.

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 answer-format rules are front-loaded and the scoring/vetting behavior follows, so an agent reading top-down gets the critical constraint first. The prose is dense with semicolon-chained clauses and a run-on first sentence, but no sentence is 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 submission tool with no output schema and no annotations, the description covers the hard parts: the answer encoding, the version-pinned nomenclature, and the practice-versus-hidden scoring lifecycle. It is only short on the return value and on where puzzle_id originates, which are the remaining gaps an agent would hit on a first call.

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 50% (notes and api_key are documented in-schema), and the description compensates well on answers, spelling out the 10-string slot-order format, the '/' candidate-list convention, INVALID for unassigned names, and UNSURE to skip. It adds nothing about puzzle_id, which is required but entirely undocumented in both schema and description, and it never mentions the optional notes 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 opens with a specific action (submit the 10 answers for an HLA report) and then defines exactly what each answer slot contains, with a concrete example (A*02:01) and the IPD-IMGT/HLA 3.66.0 reference version. The domain-specific sibling set (hla_get_report, hla_reports, hla_vet) is implicitly differentiated by the vetting/answering split, though the description never states outright that this is the submission tool versus the retrieval tool.

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?

Usage is implied rather than stated: an agent can infer it should call this after obtaining a report, and the description does route hidden-report work onward by naming hla_vet as what vets them. But there is no explicit 'call this after hla_get_report', no note on where puzzle_id comes from, and no exclusion telling an agent when not to submit.

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