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

Annotations only declare the coarse profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false). The description adds genuinely non-derivable behavior: the confirmation-email handshake, that no record exists until confirmation, that the caller never receives a password/login/token, and that the reply is identical for new and existing addresses.

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?

Dense but front-loaded: the write-tool warning leads, then the flow, then the outcome constraints, then the usage restriction. No sentence is filler despite the length.

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?

For a 4-param mutation tool with no output schema, the description compensates by explaining the async confirmation flow and what the caller does and does not receive in the reply. Nothing needed to invoke it correctly is missing.

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 100%, so email, firstName, lastName and marketingConsent are already documented. The description reinforces that email must be the person's own and hints at marketing-consent timing, but adds little syntax-level meaning beyond the schema. Baseline 3 applies.

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 an account for a person') and immediately distinguishes itself from the surrounding get_* read tools by flagging 'WRITE TOOL, not read-only'. An agent knows exactly what this does before opening the 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 precondition ('Only use this when the person asked you to') and an exclusion ('Accounts are for virtual assistants: other accounts are blocked at checkout'). Both when-to-use and when-not are covered.

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