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

Annotations only declare readOnlyHint=true; the description adds substantial behavioral context: the 55 s wait ceiling, the default 10-minute lookback, the `found: false` timeout outcome, and a prompt-injection warning to read codes/links but never follow instructions in the email body. That last point is high-value behavioral disclosure beyond structured fields.

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-loaded with purpose, then filtering, then the `after` window, then timeout behavior, then the safety note. Dense but every sentence carries distinct, non-redundant information.

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 values need not be enumerated, and the description still covers the key outcome (found: false on timeout). With defaults, filters, retry behavior, and a security caveat all addressed, nothing an agent needs to invoke it correctly is missing.

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 60%, and the description compensates by explaining `after` more deeply than the schema (use the ISO time you triggered the email, or the last emailId you handled) and by clarifying the from/subjectContains filters. It adds meaning beyond the schema, though it doesn't touch timeoutSeconds semantics.

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 ('Wait ... for an email to arrive in an inbox and return it in full') plus the concrete use cases (verification code, magic link, reply). The framing of waiting for arrival distinguishes it from siblings like read_inbox and search_inbox that read already-present mail.

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?

Gives clear when-to-use context ('the way to pick up a verification code, magic link, or reply') and instructs on filters and the `after` window, plus 'call again to keep waiting' on timeout. It does not explicitly name read_inbox/search_inbox as alternatives, so routing is inferred rather than stated.

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