delete_image

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

Goes well beyond the destructiveHint annotation by disclosing exactly what is destroyed (versions, build context, dependent apps), the exact-match confirmation requirement, the refusal condition during builds, and the extra apps:delete scope needed when apps exist. This is rich behavioral context an agent needs before a destructive call.

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?

Front-loads the destructive scope in the first clause, then layers confirmation, refusal, and scope requirements as terse, information-dense sentences. No wasted words.

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?

No output schema exists, but the description covers the destructive outcome, confirmation contract, error conditions, and scope requirements, which is everything an agent needs to invoke this mutation safely.

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 100%, so baseline is 3; the description adds value by explaining the confirm_name semantic (exact image name required, else IMAGE_NAME_MISMATCH) and the scope interaction tied to apps. The workspace_id parameter is left to the schema, keeping it at 4 rather than 5.

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 (DELETES permanently) and resource (image), and explicitly enumerates the cascade: versions, build context, and every application created from it. This distinguishes it clearly from siblings like delete_app or delete_file.

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?

Provides concrete preconditions and failure modes: confirm_name must match exactly or IMAGE_NAME_MISMATCH, and the call is refused with IMAGE_BUILD_IN_PROGRESS during a build. It does not name alternative tools (e.g., get_image before deleting), so it stops short of explicit when-vs-alternative routing.

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