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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds genuinely new behavior: the deletion is irreversible, dangling references should be checked first, the parent object record survives, and re-uploading restores a file. That is real context beyond the annotation flags, though permissions/auth requirements and any post-delete response are unstated.

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?

Four short, front-loaded sentences with the irreversibility warning placed high, and no filler. The trailing keyword block ("| EN: file, image, document, attachment, upload") is a discoverability artifact rather than agent-facing instruction, which keeps it just short of a 5.

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 single-purpose deletion tool with full annotation coverage and no output schema, the description covers the essentials: what is destroyed, what survives, the referential pre-check, and the recovery path. Only the auth/permission requirement and any error-on-referenced-file behavior are left implicit.

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 description coverage is 100%, so both file_id and file_udid are already documented in the schema and the description adds nothing about them. Baseline 3 applies when the schema carries the parameter semantics.

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 ("Eine Datei aus der strukturierten Ablage loeschen") and immediately scopes it: the object record persists and only the file is removed. That scope sentence is what separates it from the similarly-named sibling onto_object_delete, so an agent can pick correctly 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?

Gives a concrete pre-condition ("pruefe vorher, ob Objekte darauf verweisen") and points at the replacement path via the named sibling upload_file_to_object. It does not, however, state when NOT to use this tool (e.g. use onto_object_delete to remove the record itself), so the routing guidance is good but not exhaustive.

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