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

Annotations already establish readOnlyHint and openWorldHint, and the description adds real operational detail beyond them: 5-second polling, a timeout ceiling of 50, and the fact that timeout is not terminal but should be retried. It stops short of saying what a failed job looks like or whether the return value differs on timeout versus failure.

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?

Two short sentences, zero filler, and the core blocking behavior plus polling interval is front-loaded before the retry instruction. Every clause carries information an agent needs to call it correctly.

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?

For a two-parameter polling tool this covers timing and retry well, but with no output schema the description should say what comes back when the job completes, fails, or times out — the agent currently cannot tell how to interpret the result of a timed-out call.

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 50%: timeout_sec is documented in the schema with min 5 / max 50 / default 50, and the description restates the max-50 ceiling without adding much. job_id is undocumented in both places, though its meaning is self-evident from the tool name; baseline 3 fits a tool where the schema carries most of the load.

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 and resource ('Wait until a job is completed or failed') and scopes it with polling cadence and a timeout ceiling. An agent can distinguish this blocking wait from siblings like get_caption_job or list_caption_jobs, though it never names the non-blocking alternative explicitly.

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?

Gives retry guidance ('If it times out, call it again'), which is genuinely actionable, and implies usage after a job is created. It does not say when NOT to use it (e.g., prefer get_caption_job for a non-blocking status check), so the agent must infer the tradeoff against siblings.

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