job_status

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

Discloses long-polling behavior, the return format (status, progress, message, done, result?), and pacing strategy. No annotations exist, so description carries full burden. Could mention error handling if job not found, but covers key behavioral traits.

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: purpose, mechanism (long-polling, pacing), and return format. Front-loaded with core action, each sentence adds value. No wasted words.

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?

Despite no annotations or output schema, description provides return type, usage context (post-async calls), parameter constraints (wait_seconds range), and behavioral notes (blocking). Complete for a polling tool with two parameters.

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%, but description adds substantial meaning: explains job_id implicitly, defines wait_seconds with range (1–60) and behavior (blocks until state change or timeout). Far exceeds schema, fully compensating for lack of parameter descriptions.

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 it polls background job status, specifies supported job types (transcription, clip render, batch export), and mentions the long-polling feature. It distinguishes from siblings by naming specific preceding tools (transcribe_start, batch_create_clips).

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?

Explicitly says when to use this tool ('Use after transcribe_start or batch_create_clips(async_mode: true)'), describes the wait_seconds parameter for pacing, and warns about blocking behavior. This provides clear context for selection.

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