cpu_step

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

Without annotations, the description carries full burden. It states the tool enters cpu-step mode and runs ZRCP commands, but does not disclose side effects, prerequisites (e.g., machine must be running), error conditions, or how step mode is exited.

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 concise sentences with no wasted words. Front-loaded with the core purpose.

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, and the tool is complex (single-step debugging). The description omits return values, error handling, state changes, and how to integrate with other tools. Incomplete for effective use.

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 baseline is 3. The description rephrases the parameter's effect ('or cpu-step-over when step_over is set') but adds no new detail beyond the schema description.

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 'Execute a single CPU instruction' with verb and resource. It mentions the two modes (cpu-step and cpu-step-over) but does not explicitly differentiate from sibling tools like 'set_breakpoint' or 'disassemble', which have distinct purposes.

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 implies the tool is for single-stepping but gives no guidance on when to use this versus other debugging tools like breakpoints or stepping over versus into. No alternatives or exclusions are mentioned.

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