Destroy a SpicyAPI task's stored content

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

Annotations already signal destructive and idempotent behavior, but the description adds substantial context beyond them: charges remain queryable, no refund or reversal occurs, no per-output granularity, the operation is irreversible, repeat calls are no-ops, and user confirmation is required. This fully discloses the consequence profile an agent needs before invoking a destructive tool.

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 description is dense but every sentence carries a distinct operational fact: destruction scope, cost-record preservation, irreversibility, download warning, terminal-state precondition, waiting path, idempotence, and confirmation. The most critical safety information is front-loaded, and there is no redundant filler.

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 tool with no cancellation path, this description is operationally complete: it states preconditions, exact effects, non-effects, idempotence, required confirmation, and the correct workflow via task_wait. The output schema exists, so not describing return values is acceptable.

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?

The schema already covers taskId's format and the rule to only use a user-named task. The description adds further selection semantics by requiring a terminal state and clarifying that the scope is the whole task, not individual outputs. That goes slightly beyond the baseline for high schema coverage, though it does not describe the parameter format itself.

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 opens with a precise verb and resource: 'Permanently destroy one terminal task's stored content,' and enumerates exactly what is destroyed. It also distinguishes itself from sibling tools by clarifying that it does not touch cost records or cancel tasks, so there is no ambiguity against task_wait or task_retry.

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?

The description gives explicit when-to-use and when-not-to-use guidance: download wanted results first, only call on terminal tasks, wait with task_wait for queued/running tasks, and require user confirmation. It also states there is no cancellation API)Skip and no alternative for undoing, so the agent knows this is the only destructive path and how to sequence it correctly.

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