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

Annotations already mark the tool as non-read-only, destructive, non-idempotent, and open-world. The description adds substantial value beyond that: it explains that the original model remains reachable because ids are content addresses, that the result includes a before/after class diff, that assertedClasses are re-verified and costed rather than trusted blind, and that the call costs 2 compute tokens.

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 and return value, then moves to the tag/assertedClasses distinction, the resource hint, and the token cost. Every sentence carries decision-relevant information, and the dense but organized phrasing suits a complex tool.

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?

No output schema exists, but the description explains the return value (new model id and before/after class diff). Together with annotations covering safety and cost disclosure, the description provides enough context for this multi-parameter refinement tool.

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%, so the schema already documents each parameter in detail. The description still adds conceptual meaning by distinguishing that tags can only split classes while assertedClasses declares a merge and is re-verified and costed, which helps an agent choose between the two levers.

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 specific verb and resource: refining a model's parameter classes by editing tags or assertedClasses, then re-deriving. It also names the return value, a new model id plus before/after class diff, making it easy to distinguish from sibling tools like sim_classify or sim_create_model.

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 explains the two refinement levers and their different behaviors (tags split, assertedClasses merge and are re-verified), which gives clear context for how to use the tool. However, it does not explicitly name alternative tools or state when not to use this one, so it falls short of full when/when-not/alternatives guidance.

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