Start Agent Job

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

The annotations already signal destructiveHint=true, idempotentHint=false, openWorldHint=true, and readOnlHint=false. The description adds that the session is 'durable' and requires an explicit workspace, which is useful context, but it does not explain what resources are created, what side effects may occur, or what 'durable session' entails.

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 a single focused sentence with no filler. It front-loads the action and the most important constraint, making it easy to parse quickly.

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?

This is a complex tool with 8 parameters, 3 required, and destructive/open-world annotations, yet the description provides almost no workflow context, no explanation of what a 'durable session turn' means, and no guidance relative to sibling tools. The output schema and annotations help, but they do not make up for the missing high-level usage semantics.

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?

With schema description coverage at only 13% and eight parameters, the description needed to compensate by explaining key parameters like backend and prompt. It only reinforces the workspace concept and leaves required fields and config, context, file_refs, access_policy, and idempotency_key unexplained.

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 names a specific action ('Start'), a specific resource ('a durable session turn'), and a scope ('in an explicitly selected workspace'). It clearly distinguishes this from continuation tools like agent_continue and one-shot prompt tools, though it does not name any sibling explicitly.

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 phrase 'Start a durable session turn in an explicitly selected workspace' implies this tool is for beginning a new persistent agent run in a chosen workspace, contrasting with continuing or responding to an existing session. However, it gives no explicit when-to-use or when-not-to-use guidance and does not name alternative tools.

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