Continue a session

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

Annotations already declare non-read, non-idempotent, open-world behavior; the description adds that the session id stays server-side, that the jobId must belong to a finished job, and that a new jobId is returned. This gives useful state-transition 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?

Three sentences with no filler; the action, precondition, and return value are front-loaded and each sentence adds a distinct piece of information. It is short but substantive.

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 description covers the core lifecycle (finished job -> follow-up jobId) and the server-side session behavior. It does not specify error behavior, whether waitSeconds is honored as a blocking wait, or how model/reasoningEffort affect execution, but for a tool with no output schema and existing annotations it is reasonably complete.

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 documentation only covers jobId (20%), and the description enriches that by specifying it must come from a finished job. It does not explain the required `prompt` or the optional `model`, `waitSeconds`, and `reasoningEffort`, leaving those to be inferred from parameter names and sibling context.

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?

States a specific verb ('start a follow-up turn') and a resource ('existing session'), and clarifies the key input-output relationship: a finished job's jobId produces a new jobId. This distinguishes it from siblings like qoder_run (new sessions) and qoder_status, so an agent can tell what the tool is for.

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?

Clear context is provided: use it when continuing an existing session with a follow-up turn, and the input must be a finished job. It does not explicitly name or exclude alternatives such as qoder_run or qoder_cancel, which weakens routing guidance, but the 'existing session' scope makes the intended use evident.

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