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

Annotations declare readOnlyHint=true and destructiveHint=false, yet the description's primary behavior is 'Creates a text-generation task', i.e. a state-changing submission to a provider. That is a direct conflict, and the description also omits the async lifecycle (create returns a task ID that must later be queried) that an agent needs to reason about. Flagged as an annotation contradiction.

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?

A single front-loaded sentence that covers both operating modes with no filler. Nothing redundant or deferred.

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?

Seven optional parameters, no output schema, and an async task pattern: the description should explain that create yields a task ID to be polled via query and roughly what comes back. It names both operations but leaves the lifecycle and result expectations for the agent to infer from the schema alone.

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 the constraint blocks already encode requiredWhen, enums, and the model/thinkingLevel compatibility. The description only loosely maps 'product copy instructions and image URLs' to prompt/imageUrls and adds no new meaning for model, memberId, or thinkingLevel, so 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?

The description names a specific verb and resource ('Creates a text-generation task') and clarifies that the tool also handles a query mode via task ID, so an agent knows it covers both submission and lookup. It does not, however, differentiate itself from the many other generation/task tools in the catalog (e.g. nexscope_media_task_result, which looks like the generic task-polling counterpart).

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 two modes are named, and the schema's requiredWhen constraints imply create-first-then-query, but the description never states when an agent should prefer this tool over the generic media task result tool or other image/video generation siblings. Usage is implied rather than instructed.

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