build_docker_optimization_candidate

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

Annotations already flag this as destructive, so the description does not need to restate that; it adds useful context by noting that no image, command, path, build argument, network option, or Docker flag is accepted from the caller. It does not disclose what specifically gets mutated or destroyed, such as Treatment paths or cached artifacts, even though destructiveHint=true is present.

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?

The description is two sentences with the core action front-loaded and the caller-input limitation stated immediately after. No filler or redundancy.

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?

The output schema reduces the need to describe return values, and the annotations cover the destructive nature, but the description still leaves gaps around the candidate_round semantics, the session concept, and the exact workflow stage relative to finalization. For a tool with three required parameters and no schema property descriptions, this is insufficient for reliable selection and 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 schema description coverage at 0%, the description must carry parameter meaning. It maps build_kind to 'baseline or next candidate' and implies session_id through 'already-authorized' context, but candidate_round is never explained and session_id is not explicitly linked. The description does not compensate for the schema's lack of property descriptions.

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 ('Build') and a specific resource ('baseline or next candidate'), and clarifies that caller-supplied Docker parameters are not accepted. It does not explicitly name sibling tools, so differentiation from finalize_docker_optimization_candidate or the authorization tools is left to inference.

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 phrase 'already-authorized' implies this tool should be used after authorization, and 'baseline or next candidate' places it in the optimization workflow. However, there is no explicit statement of when to use it instead of preview, finalize, or inspect tools, and no exclusion criteria are given.

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