start_job

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

With no annotations, the description carries the full burden. It discloses that the job is long-running, returns immediately, and provides a job_id, which is key behavioral context. However, it lacks details on error handling, failure modes, or how the job progresses, leaving significant gaps for an async 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 extremely concise: two sentences, front-loaded with the primary purpose, followed by a precise list of supported types. Every sentence earns its place with no redundancy.

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 tool is relatively simple, and the output schema exists, but the description leaves out essential input details, especially payload_json semantics. It mentions job_id but not how to later reference or poll the job. The context is partially filled by sibling tools, but the description alone is not fully 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 coverage is 0%, so the description must compensate. While it enumerates supported job_type values, it does not explain payload_json (what format or content) or timeout_profile (how it affects execution). This is inadequate for an agent to construct a valid request.

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 starts a long-running job and returns a job_id immediately. It differentiates from siblings like poll_job and cancel_job by focusing on initiation, and lists supported job types, making the resource and action unambiguous.

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?

It implies when to use this tool: when a job type (batch_scrape, deep_research, etc.) needs to be started asynchronously. It doesn't explicitly mention alternatives like poll_job for checking status, but the list of job types and the mention of 'long-running' provide clear context for appropriate use.

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