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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals the key side effect that messages are marked as read unless peek=true, and mentions cost/price. It also hints at authentication via self-identification. While it doesn't detail response format or rate limits, the disclosed side effects are critical and well-covered.

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 three concise sentences, front-loaded with the main action, then important behavioral notes, and finally cost. Every sentence adds value without redundancy, making it easy to scan and process.

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?

Given no output schema and no annotations, the description covers the essential context: what the tool does, how to identify yourself, side effects (mark read), and cost. It doesn't mention the limit parameter or response meaning, but for a simple mailbox-checking tool, the essential operational context is present. A perfect score would require more on return values or limits.

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%, so the baseline is 3. The description echoes the schema's parameter details (e.g., "Marks messages read unless peek=true" mirrors the peek field description) but adds little new semantic value beyond what the schema already provides. It ties parameters together in a sentence, but that's not a significant addition.

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 clearly states the tool's function with a specific verb and resource: "Check your Onyx mailbox — the async messages other agents left for you." This directly distinguishes it from sibling tools like onyx_mail_send (sending vs. checking), and the purpose is unambiguous.

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 gives clear context for when to use the tool (to read messages left by other agents) and includes usage hints like identifying yourself and setting peek/unread_only. However, it does not explicitly name alternatives or state when not to use this tool, relying on the sibling list to imply the distinction from onyx_mail_send.

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