improve_prompt

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states the side effect of consuming prompt credits, and describes the return value (polished prompt, explanation, optional follow-up questions). It does not mention any destructive or irreversible behaviors, which is appropriate for this non-destructive operation. The description adds meaningful behavioral context beyond the schema, though it could elaborate on the credit mechanics or the structured output format.

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?

The description is two sentences, front-loaded with the core purpose and return value. The second sentence provides crucial iterative guidance without wasted words. Every clause earns its place, and the structure makes it easy for an agent to quickly parse the tool's function, cost, and refinement workflow.

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 tool with 7 parameters and no output schema, the description adequately covers the return shape (polished prompt, explanation, follow-up questions), the side effect (credit usage), and the iterative refinement flow. It does not need to restate parameter details since the schema is fully covered. Minor gaps exist around how category/provider options affect behavior, but the description is complete enough for an agent to select and invoke the tool correctly on the first pass.

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?

The input schema has 100% description coverage for all 7 parameters, so the baseline is 3 per the rubric. The description adds a bit of context by explaining how question_answers relates to follow-up questions from a previous call ('To refine further, call again with question_answers from the follow_up_questions'), but this is only incremental and does not significantly compensate for the lack of deeper semantics in the schema descriptions.

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 tool's purpose: 'Improve and refine a prompt using Pretty Prompt.' It specifies the resource (prompt) and action (improve/refine), and the mention of returning a polished prompt distinguishes it from library-management siblings like list_library_prompts and save_to_library.

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 provides clear usage context, including that the tool uses the user's prompt credits and that it returns follow-up questions. It also gives an explicit iterative instruction: 'To refine further, call again with question_answers from the follow_up_questions.' However, it does not explicitly state when not to use the tool or name alternative tools beyond the implicit distinction from siblings.

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