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

Annotations already indicate a non-read-only, non-idempotent, non-destructive operation. The description meaningfully contributes to those: it discloses that a call can resume or enqueue a run, can return run_busy while a run is still in progress, and can optionally wait for the reply up to a timeout. This is important behavioral information beyond the annotations and is not contradicted by them.

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 compact and front-loaded with its purpose, followed directly by invocation-relevant state behavior and outcome caveats. There is no filler or repeated schema text; every sentence earns its place.

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?

The schema already defines all three parameters, and an output schema exists for the return value. The description covers the execution model — resuming a waiting run, queueing a new one, and returning run_busy — so an agent has enough to select and invoke the correct tool. The only omitted details are related to sibling routing, which is a usage-guidance concern rather than a completeness blocker for this tool.

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 provides explicit descriptions for chat_id, message, and timeout_seconds, so the description does not need to repeat them. The phrase "Optionally waits for the reply" overlaps with timeout_seconds semantics but does not add meaningful format, constraint, or context details beyond what the schema gives. Baseline 3 is appropriate.

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 and resource: "Continue a chat with follow-up instructions or answers". It also adds a specific behavioral distinction by saying the agent "keeps its context" and by explaining that it resumes a run in needs_input or queues a new run when the previous one finished, so it is unambiguous against siblings like start_chat.

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 gives specific run-state conditions for invocation: use it when a run is waiting in needs_input or after the last run has finished. It also uses the run_busy outcome to implicitly signal that sending during active execution is not ideal. It does not explicitly name alternatives like start_chat or wait_for_run, so it falls just short of full usage guidance.

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