run_task

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

With no annotations, the description fully discloses the background execution behavior, the waiting status for agent questions, and the completion status, along with task_id for tracking. It doesn't cover error cases or resource implications, but the core behavioral contract is transparent.

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 moderately long but well-structured, using bullet points for return values. Every sentence adds value, including the default model note and references to companion tools, with no filler.

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?

Given the complexity of 5 parameters and an output schema, the description provides a comprehensive overview of the execution flow and return types. It could be improved by clarifying the remaining parameters, but the key behaviors are sufficiently covered for an agent to use it correctly.

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?

The schema has 0% description coverage, so the description must compensate. It explains the effect of the background parameter and how return values relate to task_id, but leaves cwd, model, and max_turns undefined. This partial compensation is helpful but incomplete.

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 verb 'Run' and the resource 'coding task', along with the default model. It distinguishes itself from sibling tools by outlining the asynchronous behavior and return statuses, making it obvious this is the entry point for new tasks.

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 explains when to use run_task (to start a task) and how to follow up with check_task and reply_task, providing a clear workflow. It lacks explicit exclusions or alternatives, but the context strongly implies this is the main invoking tool.

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