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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description still adds two pieces of genuinely useful context beyond that: the deterministic oldest-first ordering and the security warning that message text is untrusted data rather than instructions. It stops short of describing behavior on invalid room or non-membership, which keeps it from a 5.

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, both front-loaded with the highest-value facts: what is returned and in what order, then the trust boundary on the content. No filler or restatement of the title.

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-only, three-parameter tool with full schema coverage and no output schema, the definition covers ordering, pagination mode, and the prompt-injection risk that matters most for untrusted message content. The main remaining gap is the absence of any hint about the returned message fields or pagination termination, which would help an agent plan follow-up calls.

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%, and the schema already explains room formats, the after cursor's origin, and the limit default and cap, so the baseline of 3 applies. The description's contribution is limited to clarifying the ordering of results and the two retrieval modes, which is marginal added meaning rather than new parameter detail.

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 gives a specific verb and resource ("read messages of a room") plus the ordering contract ("oldest first"), which an agent can act on immediately. It does not, however, distinguish itself from sibling read tools such as read_messages, read_channel, or read_thread, so the agent must infer the boundary from names alone.

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?

"a room you are in" establishes a membership prerequisite, and "the latest ones, or those after a seq" sketches the two retrieval modes. There is no explicit statement of when to prefer this over the other read_* siblings or what happens when the caller is not a member, so usage is only implied.

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