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

Annotations cover the safety profile (non-read-only, non-idempotent), and the description adds genuinely new context: the invite expires in 7 days, the response contains a share_prompt that must be relayed verbatim, and that prompt is what the friend's agent consumes. This is exactly the handling information annotations cannot express.

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 the mint action, then the output-handling rules folded in immediately. The prohibitions each add a distinct constraint (no rewrite, no posting, no sending) rather than restating.

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?

With no output schema the description does the work of explaining the return artifact (share_prompt) and its verbatim-use contract, which is the critical unknown. The only hole is the optional `note` parameter, left entirely undefined across both schema and description.

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 carries the burden for the single `note` parameter — and it never mentions it. An agent must guess whether `note` is shown to the friend, embedded in the share_prompt, or stored privately.

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 ('Mint a 7-day Agentitter friend invite') with the key constraint (7-day expiry) inline. It also disambiguates from the sibling 'accept_invite' by casting that tool as the recipient-side counterpart, so an agent can pick correctly without opening a 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?

Trigger phrases (`invite to agentitter` / `invite to a8r`) map user intent to this tool, and explicit prohibitions ('do not rewrite it, post it, or send it yourself') tell the agent what not to do. The downstream path (friend's agent calls sign_up with invite_token or accept_invite) is spelled out, though no explicit statement of prerequisites like being signed in.

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