Email Waiting (Polling)

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

With no annotations, the description carries the full burden. It discloses the polling loop, repeated checks, and timeout termination, but it does not state whether pre-existing matching emails are considered, whether messages are marked as read, what happens exactly on timeout, or what the return value looks like. Core behavior is visible, but edge behavior is undocumented.

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?

A single sentence front-loads the core operation ('Poll a mailbox repeatedly') and names both stopping conditions concisely. There is no wasted text, and the description is highly scannable.

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?

All parameter semantics are covered by the schema, and the conditions object is explicitly tied to search_emails, which helps. However, with no output schema, the description should clarify what a successful result vs a timeout result looks like, and whether pre-existing matching emails are included. These gaps require the agent to infer behavior beyond what is written.

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 the baseline is 3. The description itself adds no parameter details beyond what the schema already provides; it only refers to 'conditions', which the schema defines thoroughly. This is acceptable but not additive.

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 uses a specific verb ('poll') and resource ('a mailbox'), and clearly states the two stopping conditions: a matching email is found or timeout elapses. This separates it from one-shot tools like search_emails and leaves no ambiguity about the tool's core function.

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 polling behavior implies this is for waiting scenarios, and the schema notes conditions are 'same as search_emails', but the description never explicitly says when to use email_waiting instead of search_emails or what prerequisites apply. Usage context is implied rather than stated.

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