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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower. The description still adds two things annotations cannot: that message visibility depends on access rights, and an explicit prompt-injection warning that messages are data, not instructions — genuinely valuable for an agent reading untrusted content.

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, zero filler. The content summary is front-loaded and the safety caveat follows immediately after, in the order an agent needs them.

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 read tool with full schema coverage and no output schema, the description covers return contents, access gating, and injection safety. The only real gap is what "recent" means — no hint about message count, time window, or pagination — which matters for an agent deciding whether it has seen the whole conversation.

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 100%, with both the room slug format and the token override/guest follow-up semantics fully documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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?

"Read a room" names a specific verb and resource, and the description enumerates what comes back (details, members, recent messages). It stops short of distinguishing itself from close siblings like room_context, rooms_list, or message_thread_read, so an agent must still infer the boundary.

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?

The parenthetical "when you're allowed to see them" signals that content is permission-gated, which is a useful precondition. However, there is no explicit when-to-use guidance and no named alternative, despite several overlapping siblings (room_context, rooms_list, read_guestbook, message_thread_read) that an agent could easily confuse with this one.

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