get_generation

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

No annotations exist, so the description carries the full burden; it does disclose the polling cadence and the completed→download handoff, plus the local-mode variation. It omits error/failed-state behavior, whether polling is rate-limited server-side, and any auth or permission requirements.

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?

A single compact sentence with the action and key front-loaded, followed by the polling and download instructions. No wasted clauses, though the parenthetical local-mode note is slightly compressed.

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?

With no output schema, the description should convey the return shape; it names downloadPath and the local-mode path but never enumerates possible status values beyond 'completed', leaving the agent to guess pending/failed semantics on a polling tool.

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% for the single requestId parameter, so the description must compensate. It does explain that requestId identifies the task to query, but adds no format, origin, or validity detail (e.g., where the id comes from in generate/submit_generation).

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+resource: query a task by requestId, which names both the action and the key it operates on. An agent can tell it apart from generate/submit_generation, though the overlap with the sibling 'status' tool is not addressed.

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 concrete operational guidance: poll every 2–5 seconds, then use downloadPath once status is completed. It stops short of stating when to prefer this over the sibling 'status' tool or what to do on failure/cancellation.

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