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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so 'Rein lesend' is largely redundant. The description still adds real context beyond the annotations: what a change event represents (create/update/delete) and the incremental-sync framing. It does not address cursor expiry, event retention, or what happens past max=100, which keeps it below 5.

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 operational content is front-loaded into two tight sentences: purpose, safety, usage decision, and alternative. The trailing bilingual keyword list ('| EN: changes, audit, feed, ...') is search-optimization padding that adds no decision value for an agent, though it is compact.

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 read-only, well-annotated, fully-described four-parameter list tool with no output schema, the description covers purpose, safety, and routing. The remaining gap is the shape and ordering of returned events, which is not required since no output schema exists but would help an agent consume results.

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 all four parameters are documented there (including default 50 / max 100 for limit and the id > since semantics), so the baseline is 3. The description earns an extra point by telling the agent where the required `since` value comes from (onto_watch_cursor), which is not stated in the schema.

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 ('Änderungen seit einem Cursor abholen') and immediately scopes it by the kinds of events returned (angelegt/geändert/gelöscht). It explicitly distinguishes itself from two siblings, onto_object_index (overviews) and onto_watch_cursor (starting cursor), so an agent can route without opening either 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?

Gives both sides of the decision: use for incremental synchronization, do NOT use for overviews, and names the alternative (onto_object_index) with the reason (cheaper and complete). It also points to onto_watch_cursor for obtaining the initial cursor, closing the loop on the required parameter's origin.

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