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

Annotations already flag destructiveHint=true, but the description adds genuinely new context: the output deletion is only "attempted" (best-effort, may not fully succeed) and the action "cannot be undone." That nuance about partial deletion is not derivable from any structured field.

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 short sentences, front-loaded with the action and its consequence before the safety instruction. No filler.

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 single-parameter destructive tool with no output schema, the essentials are covered: irreversibility, best-effort output cleanup, and user confirmation. Minor gap: nothing about what happens if the project is still processing or whether an error is returned when the output can't be deleted.

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?

Only one parameter, and the schema describes it at 100% coverage including provenance ("returned by all of the POST APIs that create an image"). The description adds nothing about the id, so 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 ("Deletes the image project") plus a secondary effect (deleting completed output). The name and description make the media type unambiguous relative to delete_audio_project and delete_video_project, though it never explicitly names them.

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 one useful precondition, "confirm with the user first," which is real when-to-use guidance. It gives no alternatives or exclusions, e.g. no routing to get_image_project to verify the target, and no mention of how to find the id beyond the schema.

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