Check for new messages

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

With no annotations, the description carries the burden, and it clearly discloses the 'Fetch and clear' side effect and the nuance about passive messages. It does not specify whether clearing is permanent deletion or just marking as read, nor describe the return format, 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?

The description is front-loaded with the core action and scope, then provides targeted environment-specific guidance. Both sentences earn their place, and the structure moves from 'what' to 'when' efficiently.

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 zero-parameter tool, this is nearly complete: it covers purpose, side effects, delivery behavior, and usage timing. The only notable omission is what exactly the tool returns beyond 'messages' and the permanence of the clearing behavior, especially since no output schema exists.

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?

The schema has zero parameters and 100% coverage, so the baseline is 4. The description adds contextual meaning about what 'messages' means and when results arrive, which is sufficient for a parameterless tool.

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 states a specific verb and resource: 'Fetch and clear all unread messages from all rooms.' It also distinguishes this from passive delivery and sibling tools by noting it covers 'passive ones that are never auto-delivered.' This makes the tool's unique role clear.

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?

Provides explicit when-to-use guidance: call it 'whenever the user asks what their friends said' and consider checking it when starting or finishing a task. It also distinguishes environments: Claude Code usually delivers automatically via hooks, while harnesses without hooks require this tool.

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