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

Annotations are coarse (readOnlyHint false, openWorldHint true, idempotentHint false, destructiveHint false), so the description carries substantial weight. It adds important behavioral context: the result is an external URL, it must be re-hosted to persist, generation uses the org's Replicate key, and specific Studio settings are required. This goes well beyond what the annotations or schema express.

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 concise sentences: the first states the action and output, the second gives the follow-up workflow, and the third lists prerequisites. Every sentence earns its place, and the most important information is front-loaded.

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?

For a generation tool with two simple parameters and no output schema, the description is complete: it tells the agent what the return value is, what to do with it next, and what conditions must be met before calling. An agent can invoke this tool and continue the media workflow 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 100% for both parameters (prompt and aspect), so the schema already documents them. The description does not add further detail about prompt style or aspect ratio behavior. Baseline 3 is appropriate because structured schema handles the semantic load.

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 clearly states the verb (generate), the resource (AI b-roll image), and the mechanism (text to image via the org's Replicate key). It also specifies the output shape, returning { url }. This distinguishes it from siblings like neuron_studio_generate_video and makes its role unambiguous.

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 gives concrete workflow guidance: re-host the media with neuron_studio_rehost_media so it persists, then place it with neuron_studio_apply add_image. It also names prerequisites (Business plan + image-model version configured). It does not explicitly say when to choose this over neuron_studio_generate_video, but the b-roll image use case is clear enough.

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