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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the mutation and external-service nature is covered structurally. The description adds useful context that query takes a previously returned task ID, but it does not explain that create is asynchronous, whether the returned handle must be polled, or any rate/latency characteristics.

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 sentence that front-loads the create behavior and follows with the query alternative—no waste. It is arguably under-packed rather than over-packed, but structurally sound.

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?

With 7 parameters, cross-field enum constraints, and no output schema, the description should at minimum explain the async lifecycle and what create returns. It gestures at a returned task ID ('known task ID') but omits what the create call yields and how to retrieve the eventual text, leaving the workflow partially inferred.

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%, so semantics for model, thinkingLevel, memberId, and the requiredWhen constraints already live in the schema. The description only echoes prompt/imageUrls and taskId at a high level, adding no syntax, format, or model/thinkingLevel interaction detail beyond structured fields. 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 concrete verb+resource: 'Creates a text-generation task' versus 'queries a known task ID', so the dual create/query nature is unmistakable. However, it never differentiates this from siblings such as nexscope_media_task_result or the many image-generation tools, so an agent must infer which tool owns post-creation polling.

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?

Usage is implied by the two operations: use create when you have copy instructions, query when you have a task ID. There is no explicit 'use this when…' guidance, no mention of the alternative tool for fetching results, and no note that production workflows should chain create then query/poll.

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