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

The annotations already indicate a non-read-only, non-idempotent side effect, and the description goes well beyond them by explaining the run lifecycle: resuming needs_input, queueing after a finished run, returning run_busy, and optionally waiting. This gives the agent a strong behavioral model without contradicting any annotation flags.

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?

Three focused sentences deliver a complete mental model. The key lifecycle facts are front-loaded, the run_busy behavior is explained, and no filler or repeated schema content appears.

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 output schema exists and the annotations are informative, the description is nearly complete for an agent. It could have gone one step further by explicitly pointing to wait_for_run for longer polling when timeout_seconds is 0, but the current wording is sufficient for correct invocation.

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 input schema already covers all parameters at 100% coverage, so the baseline is 3. The description adds extra meaning by framing message as the follow-up that continues agent context and by tying timeout_seconds to the 'optionally waits for the reply' behavior, which goes beyond dry schema text.

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's purpose: continuing an existing chat with follow-up instructions while preserving context. It goes beyond a generic 'send a message' by explaining the exact lifecycle behavior — resuming a run in needs_input or queuing a new run — which distinguishes it from start_chat and the other sibling tools.

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 clear operational context by specifying when a new run is queued versus when an existing run is resumed. However, it does not explicitly name alternatives like start_chat or wait_for_run as contrasting choices for starting a new chat or merely polling for completion.

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