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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds genuinely new behavior: the operation is irreversible, the protected first-look case, and the dry-run semantics when confirm is not true. This is exactly the extra 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?

Three short sentences, each carrying distinct load: what it deletes, the one prohibition, and the confirm/dry-run behavior. Front-loaded with the action and 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?

With an output schema present, return values need not be explained, and the description covers the safety-critical facts (irreversibility, protected look, dry-run). The remaining hole is the meaning/format of the required 'image' argument, which neither description nor schema resolves.

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 50%: confirm is documented in the schema, but the required 'image' parameter has no description in either place and the description never clarifies what value it expects (a look id/index). The description does add the default-behavior meaning of confirm, which partially compensates.

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 ('Delete one of the user's own looks') and scopes it to the user's own content, which separates it from delete_character/delete_clip/delete_video by resource. It does not explicitly name a sibling to route against, and the tool is named delete_image while the description talks about 'looks', leaving a small terminology gap.

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 operational context: only the user's own looks, the influencer's first look is protected, and untrusted deletes are dry-run. It does not name any alternative tool or state when to prefer this over sibling deletes, so the routing guidance is implied rather than explicit.

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