continue_task

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that full history is preserved, inherits monitoring guarantees from delegate_task (hard wait ceiling, error propagation), queues a second prompt if used while a round is running, and explains that a session is bound to its original model. These are non-obvious behaviors that the agent needs to know before invoking the tool.

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 three paragraphs, but every sentence earns its place. It front-loads the core action, then uses explicit USE IT FOR and DO NOT labels for scannability. It avoids fluff while covering purpose, usage, warnings, and parameter quirks. The structure is exemplary for an agent-facing tool description.

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 no output schema, no annotations, and four parameters, the description is remarkably complete. It covers what the tool does, when to use it, when not to use it, behavioral guarantees, and parameter caveats. It even references delegate_task for shared guarantees, which is appropriate given the sibling context. An agent has sufficient information to decide when and how to invoke this tool 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 provides descriptions for model and effort, but prompt and session_id have no schema description. The description compensates by framing prompt as the 'follow-up message' and session as the 'existing delegation session,' which clarifies their roles. It also adds critical context for the model parameter: 'Only needed if the session predates a bridge restart' and 'Must be the SAME model the session was created with.' This goes beyond the schema, though it does not mention the effort override, which is already covered by the 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 opens with a specific verb and resource: 'Send a follow-up message to an existing delegation session.' It clearly distinguishes itself from sibling tools by stating it is for continuing an existing session, and even contrasts with delegate_task, which is for launching a new session. This is not a tautology; it adds actionable specificity.

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 provides explicit USE IT FOR scenarios: 'iterating on work that came back good' and 'asking for the final summary when the answer came back empty.' It also gives clear DO NOT usage rules: avoid using while a round is running (check task_progress) and avoid switching models (use delegate_task instead). This is exemplary when/when-not/alternative guidance.

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