Build & test a full contest

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

Annotations provide only idempotent and destructive hints, so the description carries the behavioral burden. It adds substantial detail: schema validation, reference-solution judging, known-wrong-solution negative check, per-problem verification report, and the required success condition. This is exactly the kind of workflow transparency an agent needs.

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?

Two dense sentences: the first states purpose and verification steps, the second states return shape and the required postcondition. Every sentence earns its place with no filler or duplication of schema content.

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 complex 5-parameter tool, the description covers the full workflow, return format, and success criterion, and the output schema covers return details. It is slightly incomplete about the behavior when verify=false and does not explicitly state whether the contest is persisted or only returned, though 'import-ready' implies the latter.

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%, and the schema already documents each parameter including title, problem_kinds ordering, seed derivation, verify behavior, and hidden test count. The description reinforces the problem_kinds and verification concepts but adds no new per-parameter meaning beyond the schema.

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 uses a specific action—'Generate a whole contest... and verify it'—and details the verification workflow (schema-check, judge reference solution, confirm known-wrong solution fails). This clearly differentiates it from single-problem or validation siblings like generate_problem, validate_problem, and judge_solution.

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 gives clear context: this is the orchestration tool for producing a complete contest from an ordered list of generator kinds, and it includes an actionable guardrail ('require verification.all_passed before using it'). It does not explicitly name alternatives or state when not to use it, but the intended use case is unambiguous.

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