Generate a UGC ad video

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

Annotations already declare this is a non-read-only (generative) but non-destructive, closed-world operation, so the safety profile is covered. The description adds genuinely new behavior — that it blocks by default while waiting for the result — which matters for timeout handling. It does not disclose what is returned or what state exists when wait is false, or any credit/quota cost, so this is solid but incomplete.

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 with no filler, and the most important information — what gets produced — leads. Slightly more could have been spent on the sibling routing rather than repeating the wait default already documented in the 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 10 parameters (one required) and an output schema present, the return value does not need explaining, and the description covers the core pipeline adequately. What is missing is the practical consequence of wait=false and how this differs from the crowded set of sibling generation tools, which is the main thing an agent must decide before calling.

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 80%, so the baseline is 3. The description reinforces the roles of prompt ('from a brief'), brand grounding, and wait ('Defaults to waiting'), but it never disambiguates the three overlapping brand parameters (brandId, brandSlug, useDefaultBrand) or their precedence, which is the only real semantic gap left.

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?

The description gives a specific verb ('Generate') and a well-defined resource, and it decomposes the output into concrete parts (script + avatar + voiceover + captions), which tells the agent exactly what artifact it gets. It also notes the optional brand grounding. It stops short of naming which sibling to prefer over generate_video, generate_brand_video, or generate_subtitled_video, leaving overlap unresolved.

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?

Usage is only implied: the output composition suggests this is the 'full ad' choice versus a bare video or a subtitled video, and 'Optionally ground it in a saved brand' hints at the brand-bound path. There is no explicit when-to-use, when-not-to-use, or named alternative despite four similarly named generation siblings in the toolset.

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