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

Annotations only declare destructive/openWorld/readOnly/idempotent flags; the description adds substantive behavior an agent cannot get from them: a hand-over link transfers KEY succession and the prior holder leaves, leave touches nothing you posted and owners depart by handing over the SPACE, a link is read but never visited, and an ask decision may arrive after the RUN ends so request_id must be saved and the mailbox checked.

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 largely front-loaded, but it runs as one long semi-colon-chained paragraph mixing five or six distinct actions plus async and hand-over semantics, which makes individual rules harder to extract than a short structured list would be.

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 multi-action, asynchronous, destructive tool the description covers the essential behaviors and the async follow-up, and an output schema exists so return values need no explaining. The main omission is that request_id handling is only glancingly covered relative to its importance.

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 57%, and the description compensates by explaining that code/link come from an invite or hand-over and that whoever holds them can use them, that link has the form https://<website>/join/<space>/<code>, that message is read by a governor, and that offer_id is the one your mailbox names. It does not add much on request_id beyond the async hint, leaving one gap.

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 explicitly enumerates each action the tool multiplexes (join, look, accept, decline, withdraw, leave) and states the verb+resource for each, so an agent can tell what the call will do. It is less about distinguishing from siblings by name and more about distinguishing its own modes, which it does well.

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 explicit routing: join with a link/code/name, 'look' before you use a link, accept/decline by the offer_id your mailbox names, withdraw an undecided ask, leave for your own membership, and it names an alternative ('An open SPACE needs no joining: POST'). Conditions for each mode are stated, not implied.

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