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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description goes well beyond them: it discloses the cascade (all content and translations are removed), irreversibility, and the post-condition that deleting the active variant promotes the newest remaining one, surfaced as promotedVariant. That side effect is exactly the kind of behavior an agent cannot infer from the structured fields.

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, front-loaded with the destructive action and its irreversibility, then the side effect. No filler and no repetition of the title.

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 destructive 4-parameter tool with an output schema, the description covers the essential risk profile and the promotedVariant return value. The remaining gap is parameter-level: nothing explains how variantId and contentType relate or what happens if contentType mismatches, but with annotations carrying the safety profile this is a minor omission.

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 only 50%, and the description contributes nothing about the parameters — variantId has no description at all and contentType's enum has no explanation of whether it must match the variant's actual type. Only confirm and projectId are documented, and that documentation lives entirely in the schema, not the description.

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 ('Permanently deletes the specified variant') plus the cascade scope ('all of its content and translations'), which is far more precise than the title alone. It does not distinguish itself from nearby siblings like delete_project, delete_assets, or duplicate_variant, so it stops 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?

Usage is only implied: the tool is for removing a variant that is no longer needed, and 'Cannot be undone' serves as a caution. There is no explicit guidance on when to choose this over delete_project, delete_assets, or duplicate_variant, and no prerequisites (e.g., that confirm must be set) are stated in the description.

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