Check live messages

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

The description discloses the crucial non-obvious behavior: messages are marked as read, which explains why readOnlyHint=false and idempotentHint=false despite this looking like a fetch. It doesn't cover blocking behavior, rate limits, or whether all messages or only unseen ones come back.

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?

A single short sentence with no padding, and the read-marking side effect is placed where it is immediately visible. The phrasing 'Take new messages... sent to this live session' is slightly convoluted but not wasteful.

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 parameters and no output schema, the agent still has no idea what comes back (a list of messages? an empty result when none?) or whether the call waits for new messages. For a polling-inbox tool that is a meaningful gap, though the critical read-marking behavior is covered.

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?

Zero parameters, so there is nothing for the description to document; the baseline for a parameterless tool applies. No parameter semantics gap exists.

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 resource and scope are specific: new messages from teammates addressed to this live session. The verb 'take' is a little ambiguous (retrieve vs. consume), but the parenthetical clarifies the side effect and sets it apart from send_live_message.

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?

No guidance on when to call this versus siblings like live_status or team_activity, and no statement of polling cadence or preconditions (e.g., must start_live have been called first). The agent must infer the call context entirely.

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