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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds one genuinely new consequence — that deletion does not cancel or refund anything — which is valuable, but it leaves the meaning of 'existing account policy' unexplained and says nothing about deletion being permanent or how in-flight tasks are handled.

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?

Two short sentences with the action front-loaded and the consequence immediately following. The second sentence earns its place; the 'existing account policy' phrase is the only dead weight.

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 single-parameter destructive tool with no output schema, the essential minimum is present and annotations carry idempotency and destructiveness. Still missing are the source/format of taskId and any statement of what a successful deletion leaves behind, which matters for a destructive operation.

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?

There is one parameter, taskId, with 0% schema description coverage — only a regex pattern is supplied. The description says nothing about where taskId comes from or its expected form, so it does not compensate for the schema gap at all.

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 and resource ('Delete your image task'), which clearly separates it from get_image_watermark_task and list_image_watermark_tasks. The trailing qualifier 'using the existing account policy' is vague and adds ambiguity rather than precision, but the core action is unmistakable.

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?

'Deletion is not cancellation or refund' gives a useful when-not signal for anyone weighing this against cancelling work. However, it never states the conditions under which deletion is appropriate (e.g., only completed tasks, only tasks you own) nor names a concrete alternative sibling tool.

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