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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description doesn't need to establish safety. It adds useful context about the asynchronous nature of tasks — that they may not complete immediately, can require polling, and may exceed the initial polling timeout. This is consistent with the read-only annotations and adds behavioral value about the long-running/polling semantics.

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 well-structured: the core purpose is front-loaded in the first sentence, followed by a clearly labeled 'WHEN TO USE THIS TOOL' section with four concise bullets. The inline user-phrasing examples add practical value. Slightly verbose with the bullet formatting and repeated 'when a user' phrasing, but every section earns its place.

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 an asynchronous status tool with an output schema (covering return values), a fully documented 4-parameter schema, and safety annotations, the description is largely complete. It covers when to use the tool, the async/polling nature, and the timeout scenario. The only minor gap is explaining the interplay between polling, task_type, and is_preprocess, but those are adequately handled in the schema.

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 (polling, task_id, task_type, is_preprocess) are fully documented in the schema itself. The description adds only marginal context — it illustrates how task_id is used (carried from a previous session) — but doesn't substantively extend the schema's parameter documentation. Baseline 3 is appropriate given the high schema coverage.

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 states a specific verb+resource: 'Retrieves the current status and results of a previously initiated AI processing task.' This clearly distinguishes it as a status-polling tool from its siblings, which are all task-initiating tools (AI-Abs-Filter, AI-Aging-Simulation, etc.). An agent can immediately tell this is a read/check tool, not a task creator.

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 includes an explicit 'WHEN TO USE THIS TOOL' section with four concrete scenarios, including real-world example phrasings like 'Is my hairstyle ready?' and 'Check my previous request'. This is clear contextual guidance, though it doesn't explicitly name alternatives or state when NOT to use this tool. Since all sibling tools are task-starters rather than status checkers, the exclusion is implied but not stated.

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