start_new_ironclad_run_step

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

No annotations, so description carries burden. It discloses that it starts fresh and doesn't overwrite a continue run, which is useful. However, it doesn't mention side effects, permissions, or the nature of 'advertised menu action'.

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?

One sentence, no fluff. The key action is front-loaded. However, some terms like 'advertised menu action' are cryptic, but that's a clarity issue not conciseness.

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 only one parameter and an output schema, the description still leaves significant gaps: what is a 'menu action', how does profile_id affect the run, what are the prerequisites? The negative constraints help but are insufficient for confident invocation.

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 0%, and description does not explain profile_id parameter. The only hint is 'never switch profiles' which implies profile_id is used as-is, but the meaning is not clarified. The parameter has a default, but description adds no semantics.

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 it starts a fresh Ironclad run, which is a clear verb+resource. The phrase 'one advertised menu action per call' adds specificity but is ambiguous without context. Does not explicitly differentiate from step_once or autoplay, but 'fresh' implies not continuing.

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?

Gives a negative constraint 'never switch profiles or overwrite a continue run' but does not explicitly state when to use this tool vs siblings. It implies starting a new run rather than continuing, but doesn't name alternatives or conditions.

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