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

Goes well beyond the destructiveHint annotation by enumerating exactly what is destroyed in delete mode (profile, web user, memberships, tokens, passkeys) and what release mode preserves and who is notified (managers of foreign scopes). It also discloses the balance side-effect and the keep_balance escape hatch, plus the 400 error for last-admin.

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 core action, then modes, then side effects, then the precondition. Dense but every clause carries information; the only filler is the bilingual EN keyword list at the end, which is brief enough to justify itself for retrieval.

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 destructive, 3-parameter mutation with no output schema, the description supplies the destruction set, side effects, and error condition an agent needs before calling. Auth/permission requirements are not stated, which is the remaining gap.

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 a 3 would be the floor; the description still adds outcome semantics — it explains what each mode value actually does to the account and that keep_balance=1 leaves the residual balance in place rather than returning it. It stops short of restating the profile_id provenance, but the schema covers that.

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+resource (end management of a managed account) and immediately disambiguates the two modes: 'mode=delete loescht Profil, Web-User, Mitgliedschaften, Token und Passkeys' vs 'mode=release laesst das Konto leben'. The EN keyword tail (offboard, delete account, release, hand back) reinforces the intent against siblings like ontouser_team_suspend or ontouser_team_transfer.

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?

Explicit prerequisite ('Vorher ontouser_team_offboard_preview lesen') and an explicit failure condition (the last admin of a scope cannot be deleted → 400). What is missing is routing versus the closest alternatives, e.g. suspend vs transfer vs offboard, which the agent must infer.

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