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

Annotations convey readOnly=false and destructive=false, but the description adds meaningful behavioral context: this operation consumes a monthly quota ('Uses this month’s generation allowance'), is asynchronous ('Poll get_ad_generation'), and the final stitched film is available on the job rather than immediately. This goes well beyond the structured annotations.

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, dense sentences. The core action is front-loaded, followed by allowance/asynchrony and result-location guidance. Every sentence contributes either to selecting the tool or to invoking it correctly; there is no filler.

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?

Given the 100% schema coverage and the presence of an output schema, the description supplies the missing operational essentials: quota consumption, the polling endpoint, and where the final film appears. Nothing an agent needs to correctly invoke this tool is omitted.

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 parameters are already fully documented. The description only echoes what the schema already states by mentioning 'a product photo and a brief' and 'Optional style still.' It adds no new parameter semantics, warranting the baseline score of 3.

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 uses a specific verb and resource: 'Generate an Ad Lab Explain film from a product photo and a brief.' It clearly distinguishes this from siblings like generate_ad by naming the Ad Lab Explain artifact and adding the operational note to poll get_ad_generation. An agent can tell what this tool does and roughly how it differs from related ad-generation tools.

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?

The description clearly states what inputs trigger this tool ('from a product photo and a brief') and gives post-invocation guidance: 'Poll get_ad_generation.' It also warns the agent to 'Stay on Ad Lab; the stitched film is on the job,' which provides context about where results live. It does not explicitly describe when not to use this tool versus other ad generation siblings, so it stops short of a 5.

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