start_feedback_iteration

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

With no annotations, the description supplies some behavioral context: the loop is bounded and auditable, operates on an immutable run, and implies a retry loop. It does not disclose permissions, side effects, cancellation behavior, or what is created or persisted beyond the auditability claim.

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?

A single dense sentence is front-loaded with the core action and constraints. It contains no filler, though its terseness contributes to the gaps elsewhere.

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 3-parameter loop-start tool with no annotations and no schema descriptions, the description is incomplete: it omits parameter meaning, prerequisites, lifecycle relationship to record_iteration_feedback, and side effects. The output schema may cover returns, but callers still lack necessary invocation context.

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 the description never names or explains session_dir, base_run_dir, or max_iterations. The phrases 'bounded' and 'one immutable conversion run' loosely hint at max_iterations and base_run_dir, but session_dir remains unaddressed.

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 uses a specific verb ('Start') and resource ('feedback iteration'), and defines it as a 'bounded, auditable retry loop over one immutable conversion run.' It is distinguishable from record_iteration_feedback by implying a loop start, but it does not explicitly name sibling alternatives.

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?

It offers no explicit when-to-use or when-not-to-use guidance, and it does not mention related tools such as record_iteration_feedback, prepare_iteration_context, or inspect_iteration. The only usage context is the implicit retry-loop scenario.

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