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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true) by disclosing that the operation creates a copy and that child names, polls and score data are deliberately stripped — a material privacy consequence the agent could not infer. It stops short of saying whether the recipient must already have an account or what a successful/failed send returns.

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 verb and the full kind mapping, then the data-exclusion caveat, then the permission gate — a sensible order with no filler. The enum enumeration in the opening sentence is dense, but each clause carries distinct information.

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-parameter, non-idempotent outward-facing send with no output schema, the definition covers inputs, side effects and authorization intent adequately. The only real gap is what the caller gets back (confirmation, failure mode if the colleague's account is unknown).

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?

With only 50% schema coverage, the description compensates well: it explains what each `kind` value means, clarifies 'id ohne „u“' for templates, and names the source lists (`list_files`, `list_tasks`) the ids must come from. Minor friction: it refers to 'list_id aus list_tasks' while the schema field is named `id`, which could momentarily confuse.

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 concrete verb ('Sendet ... als Kopie') plus the exact resource set, enumerating all five values of the `kind` enum (template, board, stack, file, task_list) and the destination ('classdesk-Konto einer Kollegin'). An agent can distinguish this from neighbours like `share_file` or `save_template` 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?

'Nur auf ausdrücklichen Wunsch der Lehrkraft senden' is an explicit gating condition that tells the agent when not to act autonomously, and the id sources are given per kind. It does not name an alternative tool for the cases where sending is wrong (e.g. sharing within the school), so it falls short of full routing guidance.

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