rzil_trace_step

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

With no annotations, the description carries the behavioral burden, and it explains the side-effect (stepping) plus the resulting change events, including concrete examples like pc_write and var_write. It could add more about state mutation or session expectations, but the key behavior is disclosed and not contradicted by any annotation.

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 tight: the first sentence gives purpose and output, and the second provides the underlying mechanism and comparison. 'Uses aezse' is slightly obscure, but the event examples justify the sentence.

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 two-parameter tool with no output schema, the description compensates by giving event names and an argument format. It doesn't explain how count interacts with event batching or mention lifecycle requirements, but those are largely covered by the schema.

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%, so the schema already defines count and session_id. The description adds no new parameter-level detail beyond the schema, which is the baseline-3 case.

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?

States a specific verb ('Step'), a specific resource ('the RzIL emulator'), and the unique output ('detailed VM change events... exactly which variables and memory locations were read or written'). The typed-event examples like pc_write(old, new) make its purpose distinct from plain rzil_step and ESIL tracing.

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?

Clearly frames when this tool is useful: detailed typed change events rather than raw emulator tracing, and explicitly positions it as 'Superior to ESIL tracing because events are typed.' It does not explicitly contrast with the sibling rzil_step/rzil_run tools, so no exclusion rule is given, but the intended use case is clear.

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