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

Annotations carry destructiveHint=true, but the description adds context annotations cannot: a 30-day recovery window, that the response returns a sicherung_id usable with profil_wiederherstellen, and the explicit-confirmation precondition. This is substantive behavioral disclosure beyond the structured safety flags.

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-loads the destructive action, then the backup/recovery consequence, then the alternative routing. No filler; every clause conveys actionable information for calling it correctly.

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?

An output schema exists, so return format need not be spelled out, yet the description still flags the key return field (sicherung_id) and the recovery path. Nothing an agent needs to call this destructive tool safely is missing.

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 both parameters (profil_id, bestaetigt) are fully documented in the schema. The description reinforces the confirmation requirement but adds no format or syntactic detail beyond what the schema already provides, so the baseline 3 applies.

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 precise verb (Löscht) and resource (ein eigenes Profil samt Stellen-Agent), and distinguishes itself from siblings by naming what it does not cover. An agent can identify this as the destructive profile-deletion tool without opening the 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?

Gives explicit when-to-use ('nur nach ausdrücklicher Bestätigung der Person') and routes adjacent intents to alternatives: stellen_agent_einstellen with an=false to stop mails, aenderung_durchrechnen to change search fields. This is textbook when/when-not/alternatives guidance.

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