start_execution

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

With no annotations, the description carries the behavioral burden, and it discloses important traits: phases are durable and sequential, completed phases are never rerun, unsafe retries require explicit approval, and outputs/history are stored under EPHEMERAL_EXECUTION_STATE_DIR. It loses a point for mentioning confirm_unsafe=True, which does not appear in the input schema, but the core behavioral story is strong.

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?

Three sentences with no filler; the purpose is front-loaded and the phase contract is packed into a compact paragraph. The density is high, but each sentence contributes, and the structure makes the core behavior easy to absorb.

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 complex tool with 7 top-level parameters, a nested phase schema, and no annotations, this description provides a solid foundation but leaves gaps. It explains phase shape and retry semantics well but does not cover several top-level parameters and directs the agent to a non-existent confirm_unsafe parameter.

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 0%, so the description must compensate; it partially does by defining the phase object and its optional fields and by referencing resume_policy. However, it omits meaningful parameters like idempotency_key, unsafe_side_effects, execution_id, label, and top-level timeout/max_output_bytes, and it references confirm_unsafe=True, which is not in the schema.

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 opens with a specific verb and resource: 'Run a sequential, durably checkpointed set of command phases.' It also distinguishes this tool from its sibling resume_execution by noting that completed phases are never rerun, which helps an agent tell the starting tool apart from the continuation tool.

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 this is the entry point for a checkpointed pipeline and that resume_execution is the continuation path, but it never explicitly says 'use this for a fresh run; use resume_execution to continue.' It gives useful context about retrying unsafe phases, but does not clearly route the agent between alternatives.

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