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

Annotations only declare the mutation/safety profile; the description adds the operationally critical facts beyond them: it spends credits from the linked account, typically completes within a minute, and otherwise returns a task_id for async polling. Those are exactly the traits an agent needs before invoking a metered mutation.

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-loads the core action, then layers the tool/photo requirements, cost, and async behavior in tight sentences with no filler. Every clause carries decision-relevant 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?

For a metered, potentially async generation tool with no output schema, the description covers cost, expected latency, the async escape hatch, and where the tool slug originates — everything needed to call it correctly and interpret the result.

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%, so baseline is 3, but the description genuinely adds meaning beyond the schema: `tool` consumes a slug from find_kavel_tool and reinterprets `prompt` as the user's extra details rather than a standalone prompt. The photos-vs-image_urls distinction is reinforced too. It stops short of full coverage of aspect_ratio behavior, so not a 5.

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 and resource ('Create an image from a prompt, or edit the user's photo') scoped to the Kavel account, which cleanly separates it from find_kavel_tool (lookup) and check_kavel_generation (polling). An agent can identify the tool's job without opening the 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?

Gives explicit routing: take `tool` from find_kavel_tool, require a photo for photo tools (attachment in `photos` or link in `image_urls`), and fall back to check_kavel_generation when a task_id is returned. Both the when-to-use and the sibling handoffs are spelled out.

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