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

The annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the agent knows no external state is touched. The description adds useful behavior information by stating that it returns the new prompt, but it says nothing about whether the original prompt is preserved anywhere, or how kind, framework, and written_for interact.

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 lead with the action verb and the scope, then state the return value. There is no filler and nothing that should be moved earlier.

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 an output schema present, the description needn't explain return shape, and the rich schema already documents all six parameters and enums. The remaining gap is sibling differentiation against generate_prompt, which matters for tool selection on a two-tool surface.

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 the baseline is 3. The description exceeds that baseline by illustrating the abstract 'change' parameter with concrete examples ('shorter', 'add three examples', 'for a B2B audience'), which clarifies that free-form user wording is expected. It adds nothing about idea, kind, framework, or written_for beyond the schema.

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 and resource, 'Rewrites an existing prompt', and states the outcome, 'Returns the new prompt'. It never mentions its only sibling, generate_prompt, so the agent must infer that improvement means modifying an existing prompt while generation means creating one from scratch.

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 implied by the phrase 'an existing prompt with the change the user asks for', which assumes the user already has a prompt and a stated delta. There is no explicit when-to-use, when-not-to-use, or routing guidance pointing to generate_prompt for users without a starting prompt.

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