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

Annotations already establish readOnlyHint, idempotentHint and destructiveHint=false, so the bar is lower, but the description still contributes real behavioral context: it discloses the exact checks performed and explicitly promises that no secret material is returned. 'Rein lesend' partially restates readOnlyHint, but 'zeigt keine Geheimnisse' is information the annotations do not carry.

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 substantive sentence is front-loaded and efficient, but the trailing 'EN: connection, vault, key, check, health, diagnosis' keyword list is search-index noise that adds no meaning for an agent choosing or calling the tool. A shorter description would be strictly better.

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 health check with no output schema, the description supplies enough: it says what is inspected (key file, decryptability, row count) and what is deliberately withheld (secrets). Only the shape of the diagnosis result (success/failure signal vs. counts) is left implicit, which is a minor gap given the tool's simplicity.

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 there is no parameter semantics to explain; the description correctly spends no space on inputs. Baseline of 4 applies for a no-parameter tool.

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 a concrete verb and resource ('Zustand des Schluesseltresors pruefen') and enumerates the three things it verifies: key file loaded, decryption possible, row count. An agent can distinguish this diagnostic from the mutating siblings (onto_connection_save, onto_connection_remove, onto_connection_index) without opening a schema, though it never names those siblings explicitly.

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?

Usage is only implied: the 'health, diagnosis' framing suggests running it before or after connection operations, but the description never states when to prefer it over onto_connection_index or onto_connection_save, nor any prerequisite or failure interpretation guidance.

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