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

With no annotations, the description carries the full disclosure burden. It usefully reveals that improvement is performed by Claude and that each call consumes 1 credit — real behavioral facts beyond the schema — but says nothing about latency, whether the call is safely repeatable, or how the enhanced prompt is returned.

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?

Two tight sentences with no filler, front-loading the action and following with the cost. Every clause carries information an agent can act on.

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 simple two-required-parameter tool with no output schema and no nested objects, the description covers the action, the LLM backing it, and the credit cost. It is nearly complete; only the return behavior of the enhanced prompt is left implicit.

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% and both parameters are documented in the schema, including the image/video enum, so the baseline of 3 applies. The description's phrase 'rough prompt' and 'generation prompt' loosely echoes the prompt parameter but adds no format, length, or content constraints.

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 names a specific verb (improve/enhance) and resource (a rough prompt) and states the concrete output — a detailed generation prompt. That is enough for an agent to separate it from generate_image and generate_video, though it never explicitly names those siblings, so it stops short of a 5.

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?

There is no explicit when-to-use or when-not-to-use guidance, nor any named alternative. The 'Costs 1 credit' note gives a decision-relevant fact but does not tell the agent under which conditions enhancing is preferable to generating directly or to asking the user for a better prompt.

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