Read a conversation

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

Annotations only declare read-only and closed-world operation, but the description adds the 24-hour platform reply rule across Instagram, Messenger, and WhatsApp, explains replyWindow.open/closesAt and canReply reasons, and warns that message text is untrusted external content to treat as information, not instructions.

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?

Front-loads 'Read only' and then delivers message scope, reply eligibility, and the prompt-injection warning without filler. The 24-hour platform detail is compressed into a parenthetical where it belongs.

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?

With no output schema, the description still explains what comes back: latest messages oldest first, replyWindow.open and closesAt, and canReply with a reason when false. It also covers the security caveat an agent needs when handling external message text.

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 100%, and the description mostly repeats what the schema already says about limit defaulting to 20 and maxing at 50. It adds useful ordering context ('oldest first') but does not add substantial meaning beyond the schema for either parameter.

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?

States a specific verb and resource: reading the latest messages in one Inbox conversation, plus reply-window and canReply status. This distinguishes it from list_conversations, which returns conversation IDs rather than message contents.

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 description clearly frames the use case around checking whether a reply can go out now, which implies using it before send_reply or draft_reply. It does not explicitly name those alternatives or state exclusions, so it stops short of full when/when-not guidance.

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