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

Annotations already declare the mutation/idempotent/open-world profile, but the description adds far more: server-paid generation with up to 13 provider calls, retry-with-delay semantics that can incur extra charges, 200 tasks/day global and 10/IP rate limits in Moscow time, admin allowance extensions, unlisted results expiring after 24 hours, and an experimental-quality caveat. This is exactly the cost and side-effect context an agent needs before a write with no undo.

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 then usage, limits, return handling, exclusions and caveats, and each sentence carries operational weight. It is dense and runs long, but almost nothing is filler except the slightly redundant restatement of the retry cost in the final sentence.

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 and no annotations describing return behavior, the description supplies the return contract (task ID), the follow-up tool to poll, and result lifetime (24h, unlisted). Combined with the rate limits and failure semantics, it is complete enough to invoke and manage the call correctly.

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%, so the description must carry all three parameters. It handles requestId well (fresh random UUID, reuse unchanged on retry) and implies prompt via 'text brief', but displayName (max 80 chars) is never mentioned, leaving a required-adjacent field unexplained. Partial compensation only.

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 precise verb+resource (generate a new animated pet from a text brief) and explicitly separates itself from siblings with 'Do not use to publish a pet, edit an image, or create a manual administrator request.' An agent can distinguish it from get_pet_generation, get_pet, and search_pets without opening any schema.

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 an explicit trigger ('Use only when the user requests a new animated pet from a text brief'), names two sibling tools (get_pet_generation for polling, get_pet_request_info implied), and lists concrete exclusions. The when-to-use/when-not split is fully spelled out.

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