apply_corrections

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

No annotations are provided, so the description carries the disclosure burden. It does reveal two non-obvious behaviors: the operation is gated on `confirmed=true`, and results go into a new correction folder. It does not cover error behavior, permissions, idempotency, or what happens when `confirmed` is false.

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?

A single German sentence contains the action, condition, object, and destination with no filler. The key condition is front-loaded before the purpose.

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 two-parameter command with no annotations and no output schema, the description covers the action, condition, object, and destination of the operation. It omits failure/response details, but the low complexity makes that acceptable.

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?

With 0% schema coverage, the description has to add meaning, and it does: `confirmed=true` is the required condition and `proposal_id` is tied to the previously displayed suggestion. That goes beyond raw string/boolean type declarations, though it doesn't detail failure or validation behavior.

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 uses a specific verb ('Wendet ... an'), names the object ('vorher angezeigten Vorschlag'), and adds the conditional ('nur bei confirmed=true') and destination ('neuen Korrekturordner'). This makes it clearly a follow-up apply operation and differentiates it from the sibling `propose_corrections`.

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 states a precise applicability condition: only when the proposal was previously shown and `confirmed` is true. It doesn't explicitly name alternatives or exclusion cases, but the workflow context (apply vs. propose) is clear enough.

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