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

Goes well past the readOnly/non-destructive annotations: polling cadence (at least 2 seconds apart), error handling (back off on 429/503), cost (no additional charge), a security warning (content is untrusted), and the meaning of the 'pending' delivery state. These are exactly the operational facts an agent needs before calling.

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 what the tool returns, then packs prerequisite routing, cost, rate-limit behavior, and a safety note into tight sentences with no padding. Each clause carries a distinct operational fact.

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?

An output schema exists, so return-shape detail is unnecessary, and the description still clarifies the 'pending' status semantics. Covers prerequisites, limits, and safety; only minor gaps (e.g., whether pagination exists) remain.

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 only 33% — inbox_id and capability are bare patterned strings. The description compensates by stating their provenance (from create_email_inbox) and which combination to pass, which the schema alone does not convey.

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 ('List received messages in your existing inbox') plus scope ('available content', 'message IDs'). It also distinguishes itself from the one closely related sibling by naming get_email_code and its narrower job.

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?

Explicitly routes the OTP case to get_email_code and states the prerequisite chain (inbox_id, capability, access_token come from create_email_inbox). It doesn't spell out when-not to call this, but the inbound-scope constraint ('received messages in your existing inbox') implicitly excludes outbound/other mailbox scenarios.

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