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

Annotations declare non-read-only, idempotent, non-destructive behavior. The description adds some genuine context beyond them: an authorization precondition ('authorized safe boundary'), a no-polling instruction, and explicit disclaimers of guarantees ('No visitor artifact or verified external model silence is claimed'). This is real added value, though delivered in opaque language.

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?

Five sentences of cryptic, jargon-laden prose with no front-loaded statement of purpose. The wording is dense and abstract rather than economical, so the reader cannot quickly extract the operative information.

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 an 8-parameter, stateful tool with no output schema and near-zero schema coverage, the description is far too thin and obscure. It leaves the action lifecycle, the meaning of the room enum, and the effects of enter/leave/read essentially unexplained.

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 13% (just account_ref), so the description must carry the burden for 8 parameters, but it only thematically alludes to a few ('voluntary', 'safe boundary', 'credit redemption'). The action, room, visit_id, and request_key parameters are never explained in the description or schema, leaving their semantics unclear.

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 evokes 'private dwell rooms' and 'voluntary entry' but never states in plain terms what the tool actually does (e.g., 'manages a private waiting-room session'). The action enum (offers/unlock/enter/read/leave) hints at room lifecycle, but the prose is too abstract to distinguish this from siblings like eclypse_room_state or eclypse_pause.

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 offers fragments of guidance ('Voluntary entry requires an authorized safe boundary', 'Wait locally without polling'), which implies a precondition and an anti-pattern, but never says when to choose this tool over the many eclypse_* alternatives or what the intended workflow is. No exclusions or comparisons are given.

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