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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds real behavior: poll interval ('every few seconds'), per-call ceiling ('at most 50 s'), result parity with the two get tools, the retry requirement, and the cost fact that 'Waiting makes and charges nothing.' That last point is decision-relevant and appears nowhere in structured data.

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?

Front-loaded with purpose and tightly scoped, but the opening sentence is a long run-on with nested parentheses ('(or failed)', '(jobId)', '(project_id)') that slows parsing. Nearly all content earns its place; only the packing is suboptimal.

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?

Covers everything needed for a polling wrapper: what it returns (identical to the two get tools, so no output schema is needed), the time budget, the retry loop, and that it is free. Nothing an agent must know before calling is missing.

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 100%, so baseline is 3; the description still adds meaning by pairing each id with the tool whose output it returns and by stating the 50-second per-call ceiling for timeout_seconds. The mutual exclusivity of jobId/project_id is already in the schema, so the gain is modest rather than decisive.

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 (wait/poll) and resource (a generation or Cinematic Ads project), and explicitly maps each input to the retrieval tool it mirrors: get_generation(jobId) and cinematic_ads_get_project(project_id). That mapping alone distinguishes it from every sibling in the list.

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 the selecting condition ('still being made') and the alternative it replaces ('instead of asking again and again'), plus the continuation rule: 'Still being made when the time is up: call it again.' An agent knows both when to enter the loop and how to exit it.

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