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

Adds substantial context beyond the annotations: a 55s blocking window, the retry-on-found=false pattern, and the single-consumption semantics ('Each code is returned once'), which explains the non-idempotent annotation and is critical to avoid an agent re-reading a consumed code. It also names a return field (found) despite there being no output schema.

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?

Four short sentences, front-loaded with what the tool does, then prerequisites, then failure handling. Every sentence carries operational value with no repetition of the schema.

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, the description usefully discloses the found=false outcome and the returned code, plus the timeout/retry loop. It stops short of describing any other return fields or whether a failed wait has side effects, leaving a small gap for a blocking tool.

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 description coverage is 100%, so channel, from_contains, since_seconds and timeout_seconds are already documented with defaults and bounds. The description adds no parameter-level detail beyond implying email delivery, so the baseline of 3 applies.

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 a verification code (OTP) to arrive by email and return it.' This clearly distinguishes it from the read-oriented siblings like read_email, list_emails, and get_my_inbox, which do not block or consume a 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?

Gives an explicit prerequisite and ordering: 'Trigger the code first (e.g. submit the sign-up form...), then call this,' plus failure handling ('if it returns found=false, call it again'). It does not name an alternative tool for non-OTP reads, so it stops just short of full when/when-not routing.

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