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

With no rich annotations beyond non-hints, the description carries the burden of disclosing side effects. It adds important behavior: the new prompt becomes active immediately and the previously active prompt of the same type/subtype is deactivated. This goes beyond the generic 'create' verb and gives an agent accurate expectations.

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 sentences carry all essential information with no wasted words. The core action and its key behavioral consequence are front-loaded before the usage directive.

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?

Given that an output schema exists and the schema documents most parameters, the description is complete for execution. It covers the primary behavioral consequence (activation/deactivation) and the intended use case. It could have named update_prompt as an explicit alternative or explained when a new version is not appropriate, but this is a minor gap.

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 description coverage is 75%, so the schema already documents most parameters. The description reinforces the semantic relationship between type/subtype and the deactivation behavior, but does not add granular detail for the prompt value or interface_type beyond what the schema provides. This meets the baseline without exceeding it.

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 opens with a specific verb and resource: 'Create a new prompt version for the authenticated application.' It immediately differentiates the tool from siblings like update_prompt by explaining that creation produces a new version and automatically deactivates the prior active prompt. This is unambiguous and complete.

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?

It explicitly states when to use it: 'Use this whenever you want to change prompt text.' While it doesn't name the alternative update_prompt or explicitly say when not to use it, the guidance is clear and sufficient for most selection decisions.

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