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

Annotations already disclose write, non-idempotent, open-world and destructive behavior, so the description adds the useful 'capped per website' constraint and the returned identifiers. It stops short of quantifying the cap, describing failure modes when the cap is exceeded, or explaining whether retries would duplicate a prompt (relevant given idempotentHint=false).

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?

A single tight sentence: the '[write]' tag, the action, the target, the cap caveat and the return values are all front-loaded with no filler. Slightly dense packing of parentheticals and return info costs a point.

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?

There is no output schema, so stating that it returns `seliee_visibility_prompt_id` and `seliee_visibility_prompt_uuid` is valuable. However, for a destructive, non-idempotent creation tool, the description omits the concrete cap, error behavior on exceeding it, and the language parameter, leaving gaps an agent would hit at call time.

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 0%, so the description must compensate. It does explain that the target website can be given as either `seliee_website_id` or `seliee_website_uuid` and clarifies what the prompt text means, but `seliee_visibility_prompt_language` is left completely unexplained, and the required/optional split is not conveyed.

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 ('Add a prompt ... to a website') and even defines 'prompt' as 'question asked to AI providers', which removes ambiguity for a niche concept. It never names the obvious sibling (list_visibility_prompts) or run_visibility, so differentiation is left to the name rather than the text.

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 'capped per website' note implies a precondition, but there is no explicit when-to-use guidance, no mention of what happens once the cap is hit, and no pointer to listing/creating alternatives. Usage is inferable but not stated.

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