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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, but the description adds real substance on top: exactly what data is destroyed, that it cannot be undone, that pending credits on a failed project are refunded first, that it costs nothing, and that user confirmation is required.

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 dense sentences, front-loaded with the destructive scope before the precondition and the cost. The telegraphic fragments ("Free.") still carry information rather than padding.

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?

No output schema exists, and the description covers everything an agent needs: what gets removed, the precondition blocking the call, the refund side effect, the irreversibility, and the zero cost. Nothing material is left unspecified for a single-parameter delete.

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?

Only one parameter and schema description coverage is 100% — the schema already documents project_id as a uuid from create_short / list_projects. The description adds no further parameter meaning, so the 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?

States a specific verb (delete) and resource (project) and immediately scopes it: the video, thumbnail and stored source go with it. That scope distinguishes it from sibling mutations like retry_project and reads like get_project, so an agent can route correctly without opening the 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?

Explicit when-not condition (not possible while the project is being made, JOB_IN_PROGRESS) plus the named alternative to run first (wait_for_project), and an explicit human-confirmation requirement before invoking. Both the blocker and the workaround are stated, not implied.

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