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

Goes well beyond the annotations: insufficient balance returns 402 with no partial booking and no negative balance, and the idempotency key yields schon_gebucht=true instead of a double booking. The "never reuse the key for a different intent" warning is exactly the operational caveat an agent needs on a mutation. No contradiction with readOnlyHint=false / idempotentHint=true.

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?

Front-loaded with the operation and the source-account constraint, and each subsequent sentence adds a real behavior (idempotency, 402 atomicity, key hygiene). The trailing "| EN: transfer credits, budget, fund sub-agent, payout" keyword block aids retrieval but is not decision-relevant prose.

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 4-required-param mutation with no output schema, the definition covers the critical gaps: what gets debited, atomicity on failure, and the shape of a replayed response (schon_gebucht=true). It doesn't describe the success payload (new balances, ledger entry id) or permission requirements for the target managed account, which would complete it.

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 100%, so all four params are already documented, and the description largely restates reason/idempotency_key semantics that the schema carries. The one genuinely additive point is the negative constraint "es gibt kein from_profile_id", which clarifies how to_source is resolved. Baseline 3 fits since the schema does the heavy lifting.

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 ("Credits vom EIGENEN Guthaben auf ein verwaltetes Konto umbuchen") with the scope constraint that the source is always your own account, and the EN keyword tail separates it from balance/chargeup siblings. An agent can distinguish it from ontouser_team_credits or onto_credit_chargeup without opening a 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?

Explicitly rules out a from_profile_id argument and pins the source account, and gives concrete retry guidance ("nach einem Timeout gefahrlos wiederholbar"). It also warns against key reuse. It stops short of naming which sibling to use for other funding flows (e.g. chargeup vs. checkout), so the alternative routing is implied rather than stated.

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