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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, fully covering the safety profile. The description reinforces this consistency by framing the operation as retrieval. It does add one useful behavioral nuance beyond the schema — the notion of a task that 'hasn't completed yet' and the polling-timeout scenario — but the core polling semantics are already documented in the polling parameter. With strong annotations covering the burden, a mid score is appropriate.

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 opening paragraph and the bullet-point list are redundant — the first sentence already covers 'check on a task started earlier' and 'user returns to inquire,' both restated in bullets. The purpose is front-loaded, which is good, but the content could be tightened by roughly half without losing information. Reasonably organized via headers, but not tight.

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 read-only idle/polling tool with a rich output schema, strong safety annotations, and full parameter documentation, nothing critical is missing for correct invocation. The description adds the polling-timeout context and previously-initiated-task framing that the schema cannot convey. Slightly more depth on response returns could be added, but the output schema already covers that.

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 all four parameters (task_id, task_type, polling, is_preprocess) are already well documented in the schema. The description references task_id conceptually in its usage bullets but adds no new syntax or format details beyond what the schema provides. This matches the baseline-3 case where the schema does the heavy lifting.

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 uses a specific verb and resource ('Retrieves the current status and results of a previously initiated AI processing task') that unambiguously defines the tool's function. It clearly distinguishes this status-checking tool from its siblings, which are all concrete task initiators like AI-Bag-Virtual-Try-On and upload_file — an agent can immediately tell this is the polling/status companion to those task tools.

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 dedicated 'WHEN TO USE THIS TOOL' section supplies four concrete trigger scenarios, including 'When a user provides a task_id from a previous session,' 'When resuming a conversation where a task was left processing,' and the polling-timeout edge case. This is clear contextual guidance, though it never explicitly names alternatives or states when NOT to use the tool, so it stops short of the top score.

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