provision_post

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

No annotations are present, so the description carries the full burden. It discloses idempotency, the `already_posted` conflict code, immutability ('posted as an immutable entry; it is released or reversed later, never edited'), and the lack of automatic reversal based on time ('OR 960e Abs. 4 does not release a provision by the calendar'). This is excellent behavioral transparency.

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 compact and front-loaded with the core action, then key behavioral caveats, then a consequences summary. It is dense but not bloated. The 'CONSEQUENCE:' label is a slightly formal flourish, but the sentences all earn their place. Minor redundancy between 'no automatic reversal' and the consequence line is acceptable.

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 financial posting action with no annotations and no output schema, the description covers the accounting effect, source, date, idempotency, immutability, and the error code for double posting. It doesn't describe the success response or the returned structures, but since there is no output schema, the agent may still lack that info. However, given the complexity of the tool and the strong behavioral caveats, it is quite complete, with minor gaps around response/return and explicit permission or precondition checks.

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 coverage is 0%, so the description must compensate for the three parameters. It gives some meaning to `idempotencyKey` via idempotency semantics and to `provisionId` by calling it 'a drafted Rückstellung', but it doesn't explicitly explain `workspaceId` or the format/constraints of the idempotency key. The description adds value but leaves some parameter semantics to the schema or agent inference.

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: 'Post a drafted Rückstellung as ONE entry (Dr expense / Cr provision, source `provision`) dated `periodEnd`.' This clearly distinguishes the tool from the many related siblings (provision_release, provision_reverse, provision_discard, post_entry, etc.).

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?

The description clearly implies when to use it: to post a drafted provision, with a one-entry accounting booking and an idempotency key. It gives a conflict signal (`already_posted`) that tells the agent when a provision is already posted. It doesn't explicitly name alternatives or exclusions, but context makes the usage fairly clear.

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