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

Annotations declare readOnly and idempotent hints, but the description adds crucial behavioral context: the tool does not send the request, the API silently ignores unknown fields with a 201, and the response includes warnings about dropped fields. This goes well beyond the annotations and explains the real-world consequences.

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 front-loaded with the core action, then provides critical context about the API's failure mode, and ends with a directive. Every sentence adds significant value, and it is concise enough to be read quickly.

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?

Despite no output schema, the description explains the return behavior (warnings about dropped fields) and the consequence of not validating. It covers purpose, usage, behavioral details, and the API quirk, making it complete for a tool with only two parameters.

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% with descriptions for both parameters ('operationId' and 'the JSON request body you intend to send'). The description adds the 'without sending' context and mentions business rules, but does not elaborate on parameter formats or additional constraints beyond the schema, so a baseline of 3 is appropriate.

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 validates a payload against the official schema and checks business rules without sending it. This distinguishes it from siblings like roki_sandbox_try (which would send) and roki_get_schema (which only retrieves schema).

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?

It explicitly says 'Always validate before writing or shipping integration code' and explains the critical API behavior (ignores unknown fields, returns 201) that makes validation necessary. This provides strong when-to-use guidance and implicitly contrasts with actually sending the request.

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