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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description goes beyond them by disclosing the cascade (version history is destroyed), the specific refusal behavior with status code 409, and the required precondition. That is high-value behavioral context the annotations cannot convey.

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 tight sentences: the action with its destruction scope is front-loaded, the failure mode follows, and the remedy/discovery tool closes it. No filler, and the constraint is placed where an agent will read it before calling.

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 two-param delete with full annotation coverage and no output schema, nothing essential is missing: what is deleted, what else is destroyed, the blocking condition, its status code, and how to resolve it are all stated.

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% and both parameters (projectId, compositionId) are documented in the schema. The description hints at project scoping but adds no syntax, format, or ID-source detail beyond the schema. 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?

Specific verb (Delete) + resource (composition) + scope ('and its version history') plus a project-level scoping phrase. It distinguishes itself from the many sibling deletes (delete_project, delete_brief, delete_media) and the composition-family tools by naming the exact object and the cascade.

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?

Explicitly states the blocking condition (REFUSES the ACTIVE composition, 409) and gives two remedies ('make another one active first, or delete the project'), plus a pointer to list_compositions to discover which is active. This is exactly the when/when-not/alternative structure.

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