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

Annotations already declare destructiveHint=true, non-idempotent, and not read-only, so the safety profile is covered. The description adds genuinely new behavior: remove takes the person out of every #kanal, requires confirm: true, and in some home types each change is surfaced as a card the person must tap (an approval workflow). It does not mention auth/permission requirements, but it goes meaningfully beyond the annotations.

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?

It is dense and mostly front-loaded with the action list, but the three long sentences interleave action semantics with home-type-specific rules, making it sprawling and harder to scan. Little is wasted, but the structure could separate per-action documentation from cross-cutting behavior.

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?

With an output schema present, return values need not be explained, and the description covers action meaning, home-type nuance, and the confirm flow. It is nearly complete for a multi-action mutation tool; the main residual gap is any stated permission/ownership requirement for who may invoke it.

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 already 80%, so the schema documents most parameters. The description adds useful framing the schema lacks: roles come from the home's own role ids via list_members roleDefs, member ids come from list_members, and confirm is tied to remove. It gives origin and intent for parameters rather than restating types. The action enum still lacks a per-value gloss in both places.

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 purpose (changing a member's place), then enumerates the exact action verbs from the enum (set_roles, make_admin, remove_admin, remove, accept_ask, decline_ask), so an agent knows what the tool does. It references list_members as the id source, which lightly separates it from read-only siblings, but the phrasing 'a home the person runs' is idiomatic and the sibling differentiation is left partial.

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 scaffolds when each action applies by home type: company/community, an all-ages community where changes become tap cards, and a förening where accept_ask/decline_ask apply to adults asking to lead. This is clear per-action context, though it does not explicitly rule out when NOT to use the tool versus alternatives like list_members or update_home.

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