Generate

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

Annotations declare readOnlyHint=false (a write) and destructiveHint=false, so the safety profile is covered; the description adds that text-to-image/video jobs queue immediately and that wait polls up to completion. But it introduces an undefined 'reserve' concept with no corresponding sibling tool, which muddies rather than clarifies the lifecycle.

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?

Three short sentences, no filler, with the core action and modality routing front-loaded. Slightly dense but each sentence carries operational information.

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?

No output schema exists, yet the description never says what a successful call returns (e.g., a generation/job id needed for get_generation or wait_generation). The prerequisite note for image-to-video covers the main workflow gap, but the return contract is left for the agent to infer.

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 all four parameters are already documented, including wait's 120s poll cap and the aspectRatio default. The description restates wait rather than adding new semantics, so the baseline of 3 applies.

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 ('Start a Studio generation') and immediately qualifies it by modality type (text-to-image, text-to-video, image-to-video). It partly differentiates from siblings by naming upload_input, though it doesn't clearly contrast with wait_generation.

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 explicit conditional guidance: image-to-video requires calling upload_input after reserve, and wait:true is offered as an inline alternative to polling separately. However, it never names the wait_generation sibling as the non-blocking alternative, leaving that routing implicit.

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