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

Annotations only declare the safe-read profile; the description adds substantial behavior beyond that — this tool "never confirms, edits or starts a paid retry," failed results carry error.code/message/hint with automaticRetry=false, and unaccepted animationRevision gates ZIP download, metadata editing and gallery submission. That is exactly the operational context an agent needs before deciding its next call.

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 the read-only/never-mutates constraint, and nearly every sentence carries actionable state information. It is dense but slightly sprawling — the completed-result enumeration ("preview, name/description/tags" then "pet.json and spritesheet" then "other completed results include the ZIP") is fragmented and could be tightened.

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 a single required param, the description fully covers return shapes across states: completed assets, metadata, ZIP, awaiting_confirmation jobs, and structured error fields. An agent can act on the response without any additional documentation.

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 the parameter meaning; it only contributes that the generationId is "private" and scopes it to "your" task. It never mentions the 64-character hex format enforced by the pattern, nor what happens with an invalid or foreign ID, leaving a real gap.

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?

Opens with a specific verb+resource+key: "read your generation task by its private generationId." It is immediately distinguishable from siblings (generate_pet for new tasks, search_pets for listing, get_pet for the pet entity), so an agent can route correctly 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?

Explicitly states when not to use it ("Do not use to list other tasks, publish results, or start another paid generation") and names the alternative (generate_pet for new user-requested tasks). It also supplies state-specific guidance: stop polling on failure, open the private preview for awaiting_confirmation jobs, and accept animationRevision before download/edit/submit.

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