WAzion MCP Server

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 but fails to clarify critical ambiguities. The tool name suggests returning a scalar count, yet the input schema includes pagination parameters (limit/offset) typically used for listing operations. The description does not explain whether this returns a number, a list, or how pagination affects the count logic. No information on rate limits, caching, or auth requirements is provided.

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 front-loaded and brief, but contains redundancy ('Contar' vs 'Obtiene el numero') and the unexplained '[query]' suffix. While efficiently structured, the redundancy and artifact prevent a higher score.

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 the lack of output schema, no annotations, and the presence of 6 optional parameters including pagination controls, the description is insufficient. It fails to specify the return format (integer count vs array), does not explain default behavior when no parameters are provided, and leaves the count-vs-list ambiguity unresolved.

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 ('Maximo de resultados', 'Posicion de inicio', etc.), establishing a baseline score. The description adds no specific guidance on parameter relationships (e.g., whether `notification_id` overrides other filters) or query syntax for the `filter` parameter, but given the comprehensive schema, it meets minimum expectations.

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 counts unread notifications ('Contar notificaciones no leidas') and retrieves the number of pending notifications ('Obtiene el numero de notificaciones pendientes de leer'). However, it does not distinguish this from sibling tools like `get_email_unread_count` or `list_notifications`, and the trailing '[query]' appears to be an editing artifact that creates minor confusion.

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 no guidance on when to use this tool versus alternatives like `list_notifications` (which retrieves the actual notification objects) or `mark_notification_read` (which modifies state). There are no prerequisites, exclusions, or contextual triggers mentioned.

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