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

The description contributes the polling cadence and the two terminal states, which annotations (readOnlyHint/openWorldHint only) do not cover. But it omits the most important behavioral fact for a blocking tool: what happens when maxAttempts is exhausted (up to 120 attempts), i.e. whether it times out, throws, or returns a partial job.

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 and short, which is good, but 'until COMPLETED or FAILED' appears twice in two sentences, wasting the opening's emphasis. The tool-name list is dumped inline without explaining what the agent should do with it.

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 long-blocking polling tool with no output schema and three undocumented parameters, the description should state timeout/attempt-exhaustion behavior and what the caller gets back on success versus failure. None of that is present.

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 description coverage is 0%, so the description must carry all parameter meaning, and it explains none of the three: generationId, maxAttempts, and intervalSeconds go undefined. Worse, 'Checks every 30 seconds' implies a fixed interval and conflicts with the intervalSeconds parameter (2-60s), potentially misleading the agent into not setting it.

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 ('Poll an image job') and enumerates the five creating tools whose jobs it covers (create_image, create_influencer, create_thumbnail, upscale_image, create_movie_material). It is clearly separable from the wait_for_video/wait_for_clipping/wait_for_music siblings, but never distinguishes itself from the closely related image_status sibling.

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?

The list of originating tools clearly signals 'use this after one of these creation calls,' which is genuine usage context. However, no condition is given for choosing this blocking poll over image_status, nor any warning about how long the caller may be blocked.

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