Continue Agent Session

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

Beyond the annotations, the description adds useful behavioral context: the turn is 'queued' (asynchronous/non-blocking) and 'durable' (persistent), and the session must be 'authorized' beforehand. It does not elaborate on the destructive behavior implied by destructiveHint=true, but the annotation already covers that signal, so the description adds meaningful context without contradicting the annotations.

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 front-loaded sentence with no filler or repetition. Every word contributes meaning: the action is 'Queue,' the target is a 'durable turn,' and the precondition is an 'existing authorized session.'

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 tool has 7 parameters, nested objects, an output schema, and several closely related siblings, this one-sentence description is not complete enough for reliable invocation. It omits guidance on configuration, file references, idempotency, and context, and does not clarify how this differs from agent_respond or batch_prompt.

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 only 14%, so the description needed to compensate by explaining key parameters, but it only hints at session_id via 'existing authorized session.' It says nothing about workspace, prompt, config, context, file_refs, or idempotency_key, leaving the agent to infer their roles from the bare schema.

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 verb ('Queue') and resource ('a durable turn against an existing authorized session'), which clearly communicates that this tool continues an already-running agent session rather than starting a new one. It distinguishes from siblings like agent_start and agent_fork, though it does not name them and 'durable turn' is somewhat jargon-heavy.

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 'existing authorized session' implies the tool should be used when a session already exists and is authorized, which provides some usage context. However, it gives no explicit guidance about when to prefer this over agent_respond, agent_fork, batch_prompt, or prompt, and lists no alternatives or exclusions.

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