Buchungen eines Belegs entfernen

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

The annotations (destructiveHint: true, readOnlyHint: false) already disclose the destructive nature, but the description adds crucial behavioral context: it removes data from the real client tenant, affects only non-finalized posting lines of the specified receipt, leaves the receipt itself unchanged, and requires reading the affected records first and presenting them to the user.

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 description is well-structured: it front-loads the core action, then adds usage routing, scope constraints, and safety warnings. It is appropriately sized for a destructive, risky operation. Every sentence carries meaning, though a bit long.

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?

Given the destructive nature, the presence of an output schema (so return values need not be explained), and the single fully described parameter, the description covers all needed context: scope, alternatives, implications, and a data-safety instruction. It is complete for an agent to call it correctly and safely.

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 schema already fully documents the single parameter, including that it addresses the receipt (not an individual posting line) and how to find it via bb_receipts_search. The description reinforces that it is the receipt that is addressed, but adds little beyond the schema's 100% coverage.

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 highly specific verb+resource in German: it un-confirms the postings of a receipt, thereby removing them. It distinguishes itself from bb_postings_unconfirm_for_transaction and bb_postings_unconfirm_free by naming those alternatives and the conditions under which they apply.

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 explicit when-to-use guidance ('to reverse an incorrect receipt posting while it is not yet finalized') and routes the agent: for linked transactions use bb_postings_unconfirm_for_transaction, for free postings use bb_postings_unconfirm_free, and for finalized postings use bb_postings_cancel. It also states exclusions: always removes all lines, not a single split line.

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