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

The annotations are minimal (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description carries the full burden of behavioral disclosure. It adds substantial context: no LLM call, prerequisite of owner and plan, the dependency on verification to enable run_benchmark, and the requirement for GeneratedJsonSchema objects in schema-generation. This goes well beyond the annotations and is accurate with no 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 a single, well-organized paragraph. It front-loads the core purpose, then delivers critical caveats (verification, schema-generation type, sample-generation rejection), then prerequisites, dependency, and a doc link. Every sentence adds value; there is no redundancy or fluff.

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 the tool's complexity (5 parameters, nested objects, output schema), the description covers all essential context: when to use it, constraints on reference types, verification requirements, prerequisites, and the downstream effect on run_benchmark. The link to documentation provides further detail. Nothing an agent needs to call this correctly 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?

The input schema already has 100% coverage, so the baseline is 3. The description adds meaning by clarifying the semantics of reference_verified (explicit sign-off, not a generated answer), the type restriction for schema-generation (GeneratedJsonSchema objects), and the rejection of references for sample-generation. This enriches the schema's parameter descriptions, particularly for reference_verified and reference_output, justifying a 4.

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 clearly states the tool's action: saving the gold reference for enrichment or schema-generation benchmarks. It distinguishes itself from siblings by clarifying the scope (enrichment/schema-generation, not sample-generation) and by noting it enables run_benchmark. It also specifies prerequisites, making the purpose 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?

The description gives explicit when-not-to-use guidance: sample-generation scenarios reject references, and reference_verified should only be set true after verification or sign-off. It also states requirements (owner and plan with benchmarks). However, it does not explicitly name an alternative tool for setting references in sample-generation scenarios, so it falls short of a 5.

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