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

The annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'Rein lesend' is largely repetition. What the description does add beyond the annotations is the cursor's contract: it marks the point up to which changes have been consumed, which explains why reading it is safe to repeat and how it composes with onto_watch_changes. It stops short of stating the return shape or whether the cursor advances implicitly.

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 workflow instruction is front-loaded and each sentence carries meaning. The trailing '| EN: changes, audit, feed, monitoring, event log, cursor' keyword block is search-engine padding rather than agent guidance, which keeps it out of the top band.

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 zero-parameter read tool with no output schema, the description supplies the concept that matters: what the cursor is and how it sequences with the change-fetching sibling. It does not describe what the returned value looks like (timestamp, token, opaque string), which is the one thing an agent must infer before using 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?

The tool takes zero parameters, so the baseline is 4 and there is no parameter semantics for the description to compensate for. Nothing here misleads about inputs.

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 states a specific verb and resource ('den aktuellen Beobachtungs-Zeiger lesen') and immediately defines what the cursor represents ('Stand, bis zu dem Aenderungen abgeholt wurden'). It distinguishes itself from onto_watch_changes and onto_object_index by name, so an agent can route correctly without opening any schema.

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 gives an explicit three-step workflow ('erst Cursor lesen, dann Aenderungen abholen, dann den Zeiger weiterruecken') with the rationale that this avoids gaps and duplicates. It also names an alternative for a different need ('Fuer den Volltextbestand nimm onto_object_index'), which is exactly the when-to-use/when-not guidance the dimension rewards.

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