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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, but the description adds genuinely new behavioral detail: the operation is permanent and irreversible, requires user confirmation, and cascades (deleting a project removes everything in it; segment_extra removes scene layers). It does not discuss failure modes or partial-failure behavior, which keeps it from a 5.

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 critical irreversible/confirm warning is front-loaded in the first sentence, and every following clause carries type-specific information. The hard line-wrap formatting (breaks mid-sentence and mid-phrase) makes it slightly harder to scan than a flowing paragraph, but there is no filler content.

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, non-idempotent tool with no output schema, the definition covers what gets destroyed, the confirmation requirement, cascade scope, and unsupported targets. What is missing is post-deletion feedback (what the caller receives, how to verify success), which is a modest gap given annotations already flag destructiveness.

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 description coverage is 100%, so the baseline is 3, but the description goes further by giving semantic meaning to the enum values ('asset: a character, environment or object', 'music_track: a background music track'), which the schema only labels. It still relies on the schema for id/project_id/segment_number mechanics, so it is not a 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?

Opens with a specific verb+resource ('Permanently delete') and then enumerates exactly what each supported type removes (project, asset, music_track, segment_extra). The per-type breakdown lets an agent distinguish this destructive tool from siblings like assets_edit, segment_edit, or storyboard_edit without opening any schema.

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 a clear precondition ('irreversible, so confirm with the user first') and an explicit exclusion ('a segment's image, clip and voiceover can't be deleted'), which steers the agent away from unsupported calls. It stops short of naming alternative tools for removing those unsupported artifacts, so it is not a full 5.

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