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

With no annotations, the description carries the burden and does well: it caps the wait ('max 50'), discloses the three possible return states and what each means, and lists the digest fields. It omits error/timeout-expiry behaviour and any auth or rate-limit notes.

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?

Two compact sentences with the timeout constraint front-loaded and the return states following. Dense but every clause carries information; the digest field list is slightly crammed but earns its place.

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 three simple parameters, no output schema, and no annotations, the description covers the timer, the states, and the eventual payload. The main residual gap is what the agent should do when the timeout expires without a report.

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 67% — key and token are documented, timeout_s is not — and the description compensates by explaining timeout_s as a wait duration with a max of 50. That adds real meaning beyond the schema's bare minimum/maximum bounds.

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 opens with a specific verb and resource: 'Wait ... for the email sent to a test address to be analysed', and it enumerates what the finished digest contains. It is easy to distinguish from create_test_address, but there's no explicit contrast with the sibling get_report, so the agent must infer the division of labour.

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?

Polling behaviour is implied by 'call again' on the waiting/received states, which is useful operational guidance. However, it never says when to prefer this over get_report, nor what to do if the timeout elapses — usage 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.