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

With no annotations, the description carries the full load and does well: it discloses asynchronous behavior ('a simulated human handles your orders about 20 seconds later'), data retention (deleted after 7 days), the fact that nothing is physically shipped, and the credential return. It does not say whether repeated calls create multiple demo mailboxes or replace an existing one, which is the main remaining ambiguity.

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 compact, front-loaded description with no wasted sentences: what you get, how it behaves, what it returns, and its expiry are all stated in a single tight passage.

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?

No output schema and no annotations, so the description must cover returns and side effects — it names api_key, the simulated-human delay, and the 7-day deletion. The only real gap is the three undocumented optional parameters, which are plausibly non-essential telemetry.

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?

Three parameters with 0% schema description coverage, and the description never mentions found_via, agent_name, or agent_model. All are optional, which limits the damage, but an agent has no idea whether these are attribution metadata it should populate or ignorable telemetry.

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 (start a demo mailbox) and immediately delimits it as a free, no-registration sandbox versus a real mailbox. The inclusion of play money, sample letter, sealed parcel and gift card code makes the scope unambiguous, and 'demo' plus 'no registration' implicitly separates it from register_mailbox.

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?

Establishes a clear context: this is the bootstrap step, since it 'Returns an api_key for all other tools'. It also flags the trial nature (deleted after 7 days, nothing shipped). It stops short of naming register_mailbox as the alternative for a persistent/real mailbox, so there is no explicit when-not clause.

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