register_account

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

With no annotations at all, the description carries the full burden and does well: it discloses that no API key is needed, that the password doubles as the Aivy app password, and that the reply is identical whether or not the address already has an account (an anti-enumeration property an agent could otherwise misread as confirmation). It stops short of saying whether an existing account is modified or left untouched when the email is already registered, which matters for a mutating call with zero annotation coverage.

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 the action and the step marker, and every sentence adds new information — nothing is filler. The final sentence chains two ideas together ('reply looks the same...' plus the spam/sign_in fallback), making it slightly denser than it needs to be, but nothing is wasted.

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 needn't be specified, and the description still flags the one ambiguous return property (identical reply for new vs. existing accounts). For a human-in-the-loop, unauthenticated mutation the critical pieces — no API key, password sourced from the user, follow-up tool — are all present; only the two unused parameters and the existing-account side effect are left unexplained.

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 0%, so the description must supply all meaning, and it only covers two of four parameters: `email` (code is sent there) and `password` (8+ character minimum, doubles as the app password, must come from the person). `locale` and `display_name` are never mentioned, leaving a real gap that the bare schema does not fill.

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 ('Create an Aivy account from the chat') and immediately positions it as 'step 1 of 2', which separates it cleanly from the sibling verify_registration. An agent can tell it apart from sign_in and verify_registration without opening any schema.

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 next-step workflow ('ask them for the code and call verify_registration') plus a fallback branch when the code never arrives ('check spam or use sign_in instead'). It also gives a hard exclusion on password handling ('Ask the person to choose the password... do not invent one'), which is exactly the kind of when/when-not guidance that prevents misuse.

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