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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=true. The description adds the traits that actually matter: the call is an upsert (re-invoking changes role/end), 'end' revokes access, ownership is implied ('eigene Klasse'), and a precise privacy carve-out (Wunschbox, Lernjournal, Elternseite, Förderung stay private). It also discloses that the same tool doubles as a read-only listing when email is omitted — context the annotations cannot convey.

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 and free of filler; every clause (roles, until, re-invocation, list mode, revocation, privacy) carries distinct information. The heavy parenthetical packing makes it denser than ideal for scanning, but nothing is redundant.

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 six-parameter, mode-switching tool with no output schema and thin annotations, the description covers what an agent must know: which arguments select which mode, what the mutations do, what is never exposed, and how to undo a grant. No meaningful gap remains for correct invocation.

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 only 50%, and the undocumented parameters are the most consequential ones (email and class_id). The description compensates fully: presence/absence of email toggles the tool's entire mode, role values are expanded into concrete permissions, until is given a format and an omit-default, and class vs. class_id and end are tied to the listing mode that produces the id.

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?

The description opens with a specific verb and resource in the user's domain ('Gibt eine eigene Klasse ... frei') and immediately enumerates the three operating modes (share with email, list without email, revoke with end). No sibling tool covers class-level sharing, and the boundary against 'share_file' / 'send_to_colleague' is implicit but unambiguous from the resource named.

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?

It explicitly states when to use each variant: with email = grant access; without email = list current access holders; with end = terminate a specific grant; repeated calls = change role/end. It also gives the decision rule between the two roles (cover vs. edit) with concrete capability differences, which is exactly the guidance an agent needs before choosing an argument.

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