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

Annotations only declare readOnlyHint=true; the description adds the crucial nuance that loading saves nothing and only a human 'Freigeben' click writes, so the read-only hint is contextualized rather than merely restated. It further discloses host-UI dependency and a security constraint not to expose hidden approval metadata or infer approval from chat text.

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?

Short and front-loaded: the trigger, the safety constraint, and the forbidden action each get one sentence, with the read-only guarantee placed early. The telegraphic fragments ('No save on load. Only its Freigeben click writes.') read awkwardly, but nothing is padding.

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?

Safety and host-UI behavior are covered thoroughly, and no output schema means return values need not be explained. However, for a tool whose only real complexity is the polymorphic change object, that dimension is left entirely to the schema, leaving the definition only partly complete.

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 0%, so the description must carry parameter meaning, and it largely does not. 'Use the exact read revision' hints that expectedRevision must match a previously read revision, but the four change variants (role, access, invite, revoke_invite) and their required fields are never mentioned; the agent must reverse-engineer them from the oneOf.

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 verb/resource pair is recognizable ('show normalized before/after values in the human Owner card') for a team-change approval preview, and it explicitly separates itself from confirm_team_change. The phrasing 'use the exact read revision and change' is convoluted and never plainly states that this renders a preview/diff card rather than executing anything, so it is clear but not crisp.

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 gives a triggering condition ('after an explicit team change request') and an explicit negative path: with no host UI there is no write, fall back to the existing settings page. It also rules out calling confirm_team_change from the model, which is genuine routing guidance. It stops short of naming which prepare_* tool supplies the revision/change pair.

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