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

Annotations already declare readOnlyHint=true, so safety is covered. The description goes beyond by disclosing polling behavior, expected latency per media type, and what the agent should tell the user while waiting — useful operational context. It stops short of noting rate limits or a max-polling cutoff.

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-loads the purpose, then usage, then parameter guidance, then return shape — a logical order. Slightly verbose in the polling-timing paragraph, but every part earns its place given there is no output schema.

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 compensates by enumerating the return fields (`status`, `output`) and their values, and it covers the full call lifecycle including re-polling. An agent has everything needed to invoke and interpret this 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 description coverage is 100%, so the baseline is 3. The description reinforces the type-to-category mapping with concrete examples ('images' for text-to-image/image-to-image/inpaint-image), which is helpful routing context, but it largely restates what the schema property descriptions already say.

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: 'Check the status of a queued or processing generation request.' Clear what it does. However, it never distinguishes itself from the fetch-image, fetch-video, and fetch-audio siblings, which an agent could easily confuse with this generic poller — the `type` parameter is the only hint at the difference.

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?

Explicit trigger ('use this tool when a generation tool returns a status of "processing"'), explicit loop condition ('call it again while the status stays "processing"'), and explicit user-facing guidance about job duration. Nothing is left to inference.

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