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

Annotations declare readOnlyHint=false (a mutation) and idempotentHint=true; the description usefully narrows what that mutation touches — only the read status, not content, and nothing is deleted — and adds that the message remains retrievable. That resolves the ambiguity of a non-read-only tool that is also non-destructive.

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 three German sentences are well front-loaded and earn their place, but the trailing '| EN: end user, customer, portal, notification, map, scope' keyword block is SEO-style noise that adds nothing to tool selection and dilutes the structure.

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 one-parameter idempotent flag flip with no output schema, the description covers purpose, precondition, and post-state ('Die Meldung selbst bleibt abrufbar') sufficiently. Only the reused id parameter lacks description-level elaboration, and the schema already handles it.

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 100% and the single parameter's schema text already says the id is a 'Notification-id aus ontouser_notification_index'. The description restates that same provenance, so it adds no meaning beyond the schema; baseline 3 applies.

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 first sentence states a specific verb and resource ('Eine Benachrichtigung als gelesen markieren'), which is unambiguous and clearly distinct from listing (ontouser_notification_index) or sending (ontouser_notification_send). It stops short of explicitly contrasting itself with those siblings, so it is clear but not fully self-differentiating.

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?

'Nutze es nach ontouser_notification_index' gives explicit sequencing guidance that tells the agent when this tool is applicable and where the id comes from. There is no when-not guidance, but with a single meaningful alternative in the notification group the omission is minor.

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