wait_for_job

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

With no annotations, the description carries the full burden of behavioral disclosure. It adds useful context by stating it returns 'bounded logs' and 'Artifacts,' implying logs are truncated or limited. However, it does not disclose behavior when timeout_seconds is reached, what happens if the job_id is invalid, or whether the wait is a long-poll. The missing timeout semantics are a notable gap for a blocking operation.

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, concise sentence that front-loads the purpose ('Wait for a durable job') and lists the return values. There is no extraneous information, making it highly efficient and easy to parse.

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 simplicity of the tool (two parameters) and the presence of an output schema, the description covers the core purpose and return values. It is missing details about timeout behavior and error conditions, but for a simple wait tool, it provides adequate completeness. The lack of annotations raises the burden on the description, though the essential context is present.

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 provides parameter names, types, and defaults but no descriptions (schema_description_coverage is 0%). The tool description does not compensate; it never mentions job_id or timeout_seconds. While parameter names are self-explanatory, the description adds no meaning beyond the schema, especially for timeout_seconds, whose semantics (e.g., timeout behavior) are entirely unaddressed.

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 function: waiting for a durable job and returning specific outputs (state, exit code, bounded logs, artifacts). It uses a specific verb ('Wait') and resource ('durable job'), which differentiates it from siblings like get_job_status that likely return current status without blocking.

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 implies usage via the verb 'wait' but does not explicitly state when to choose this over alternatives such as get_job_status, get_job_logs, or cancel_job. It lacks explicit context like 'Use this when you need to block until completion' or 'For non-blocking status, use get_job_status,' so usage context is implied rather than directly conveyed.

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