start_step

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

Beyond the annotations (destructive/openWorld), the description adds that prepare downloads pinned trusted sources and builds may fetch dependencies, that external steps are gated behind XBOX_PORT_ALLOW_EXECUTION=1, and that the result is an async job id rather than a completion. Those are concrete operational facts an agent could not infer from the annotations. It doesn't disclose what each destructive step overwrites or whether a failed step leaves partial state.

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?

It is front-loaded: the core action and its main constraint come first, followed by per-step and execution-gate details. Every sentence carries operational information, though the flat re-listing of the step enum largely duplicates the schema and only 'prepare' receives elaboration.

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 an async, destructive pipeline tool the description covers gating and return semantics well (and an output schema exists, so return shape needn't be restated). However it never explains workspace_id, whether steps must run in a given order, or whether a workspace must be created first via create_workspace — gaps that affect correct 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?

With 0% schema description coverage, the description must carry parameter meaning. It explains the step enum values and adds a conditional constraint on input_path (an allowed ISO path, required for extract), which is useful. workspace_id, the other required parameter, is never mentioned — no scope, format, or prerequisite — so compensation is only partial.

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 first sentence gives a precise verb+resource ('Start a fixed profile step') and an explicit negative constraint ('never arbitrary shell text') that rules out a shell-execution interpretation. It then enumerates the exact valid step values, so an agent knows this is a bounded pipeline initiator. It stops short of 5 only because 'fixed profile step' and what each step actually performs remain partly opaque.

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 gives real when-to-use conditions: 'extract needs an allowed ISO input_path', external steps require XBOX_PORT_ALLOW_EXECUTION=1, and prepare/builds may fetch sources. These are prerequisites that select correct invocation paths. It does not name sibling alternatives (e.g. get_job for polling) explicitly, leaving that inference to 'Returns a job id, not a completion claim'.

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