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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds the substantive behavioral split the annotations cannot express: project and music_track deletes are permanent ('for good'), while asset and segment_extra go to a recoverable bin. It also discloses cascade behavior for projects ('it and everything in it') and that segment_extra takes its scene layers with it.

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 safety-critical instruction is front-loaded in the first clause, and every subsequent phrase maps to a distinct entity type or exclusion. It is dense and slightly telegraphic but has no filler sentences.

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 4-parameter destructive tool with no output schema and full schema coverage, the description covers permanence, cascade scope, bin recovery, and non-deletable parts. It omits what the call returns (deleted object vs. status) and whether a binned item can be restored by another tool, which are the only remaining gaps.

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 the baseline is 3, and the description earns an increment by defining what each enum value actually targets (asset = character/environment/object, segment_extra = sound effect or overlay) and by bounding the operation. It still relies on the schema for the id/project_id/segment_number pairing rules rather than restating them.

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?

The description names a specific verb (delete) and enumerates the exact resource types it accepts (project, asset, music_track, segment_extra), plus the sub-entity meaning of each. It doesn't need sibling differentiation because no other sibling is a delete operation, but it also doesn't state the target resource singularly that would push it to 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?

'Confirm with the user first' gives an explicit precondition agents must satisfy before invoking, and the closing line establishes a negative case: a segment's image, clip and voiceover can't be deleted. It stops short of naming an alternative tool for the excluded cases, so no explicit sibling routing.

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