List recoverable GPTProto tasks

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds behavioral context beyond annotations by mentioning tasks are 'saved locally' and that the list includes 'completed result URLs', which provides useful detail about the operation's nature and output. No 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?

The description is two sentences, front-loaded with the core purpose and followed by a clear use-case sentence. It contains no fluff, and every word adds value. Structure is optimal for agent consumption.

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?

The description lists the returned fields, which partially compensates for the lack of an output schema. However, it doesn't explain the filtering parameters (limit, model, status, resource), pagination behavior, or what 'recent' means. Given the tool has four optional parameters and no schema descriptions, the description should offer more detail on parameter usage and potential edge cases to be fully complete.

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 0%, meaning the schema provides no explanations for limit, model, status, or resource. The description does not compensate by explaining how these parameters filter the list or what values they accept. While parameter names are somewhat self-explanatory, the description offers zero guidance on using them, which is a significant gap given the low 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 clearly states the tool lists recent asynchronous tasks saved locally, specifies the exact fields returned (IDs, model, type, time, state, result URLs), and implicitly differentiates from task_get by focusing on the plural list. The verb 'list' and resource are specific and unambiguous.

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 explicitly states when to use it: 'after an interrupted tool call or in a new conversation before creating another task.' This gives a clear scenario. It doesn't explicitly name alternatives like gptproto_task_get or gptproto_task_wait, but the context implies checking existing tasks before creating new ones, which is adequate guidance.

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