Notificaciones

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so the safety profile is covered without the description. The description adds the useful detail that results span multiple notification types, but says nothing about ordering, pagination, or volume — relevant since there is no output schema.

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?

It is a single short fragment with zero waste, but it is under-specified rather than concise: no action verb, no front-loaded purpose statement, and it is written in Spanish while all sibling tool names and most agent-facing context are English.

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 list tool with no output schema, the description should say roughly what comes back (fields, read/unread state, ordering) and how it differs from get_unread_count and mark_notification_read. None of that is present, leaving the agent to call it blind.

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 tool takes zero parameters, so the schema imposes nothing to explain; baseline 4 applies. The description correctly implies no filtering inputs are needed.

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 the resource (account notifications) and enumerates the notification categories it covers — AI alerts, commands, devices — which helps distinguish it from siblings like list_commands or get_unread_count. However, it is a noun fragment with no verb: it never states that it *lists* or returns them, leaving the action to be inferred from the tool name.

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?

There is no guidance on when to call this versus get_unread_count or mark_notification_read, no mention of prerequisites, and no exclusions. The agent must guess from the tool name alone.

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