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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, but the description never explains what is destructive or why repeats are not idempotent. It does add genuinely new behavioral context by describing the repeat-until-terminal loop, which annotations cannot express.

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 tight sentences with the core action front-loaded and no filler. Every clause earns its place by covering the prerequisite work and the loop exit condition.

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 looping, no-output-schema tool, the description covers the essential loop semantics and the prerequisite of doing model work first. It omits only secondary detail such as what an unsuccessful terminal state looks like or how store selection affects the call.

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 100%, so run_id, call_id, reply, and store are already documented in the schema. The description adds nothing about parameter formats beyond implying repeated `reply` calls, so the baseline 3 applies.

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 a specific verb and resource: answering the prompt a step is waiting on, which clearly differentiates it from getStep, startStep, and ask. It does not explicitly name a sibling or contrast with one, so it falls just short of a 5.

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 clear operating context: do the model work in the step's `system` and `messages` first, and keep replying until the step is done or failed. This explains the loop condition well, but gives no guidance on when to choose this over the sibling `ask` tool.

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