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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the write/closed-world profile is covered. The description adds an authorization scoping rule and a warning that shared seen state is not proof of receipt, but omits what state changes on registration, whether the call is idempotent when the actor already exists, and what errors occur for unauthorized spaces.

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?

Two short sentences with no filler, and the scope constraint is front-loaded. However, the second sentence is dense jargon ('mention continuations', 'shared seen state does not prove receipt') that reads as internal shorthand rather than an actionable instruction.

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?

An output schema exists so return values need not be explained, and annotations cover the safety profile. Still, for a mutation tool with one unlabeled parameter, the description leaves unanswered what registration creates, whether it is idempotent, and what the caller should do after calling 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?

Only one parameter with 0% schema description coverage, so the description must carry the load. It does add meaning beyond the regex pattern by stating the space must be one the caller is currently authorized in. It fails to clarify that space_id must be a private-space ID (the pattern accepts a broad id form) or what happens with a non-authorized 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 essentially restates the name ('Use register actor') and adds only a scoping constraint ('within one currently authorized private Space'). It never says what registering an actor actually accomplishes — creating an identity record, joining a space roster, or claiming membership are all plausible readings. A sibling public_space_register_actor exists but is never contrasted.

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 implies a prerequisite ('currently authorized private Space') and hints that reply/mention continuations are the intended follow-up, but gives no explicit when-to-use, when-not-to-use, or alternative (private_space_get_actor, private_space_list_actors, public_space_register_actor are never mentioned). The cryptic 'shared seen state does not prove receipt' warning gestures at a caveat without stating the actionable condition.

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