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

Goes well past the annotations: states the mutation is incomplete by design ('You cannot sign, set a password or confirm the email for them, and nothing is created until they do'), gives link lifetimes ('valid 24h'), and describes the post-confirmation landing state. It also discloses the return payload (previewUrl, manageUrl, signupUrl) despite there being no output schema.

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 correctly (purpose, then eligibility, then consent, then intents), but it is one dense run-on paragraph where the intent enumeration is buried in semicolon clauses. It also repeats itself: previewUrl/manageUrl are explained twice and 'signupUrl' is introduced then re-recommended at the end.

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 an 8-parameter tool with a deeply nested blueprint and no output schema, the description covers the risky parts well: consent, input provenance, intent-to-payload mapping, and returned links. It is only short of complete because `lang` is undocumented and country-handling is left implicit.

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?

With only 38% schema coverage, the description carries real weight: it defines all five intent values and, critically, binds each to the right payload (blueprint for business/partnership/idea, aboutText for join, wishText for order) and warns against sourcing name/email from memory. The gap is `lang`, which is never mentioned, and `countries` gets only an indirect mention ('prefilled with their name, email and countries').

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?

Opening sentence gives a specific verb ('Prepare'), a specific resource ('a 1lev1 signup') and a hard scope condition ('for a person who has NO 1lev1 account yet'), so the agent can tell this apart from prepareForSomeoneElseTool or proposeRikmaBlueprintTool without opening a schema. The 'one screen' framing further explains what 'prepare' actually produces.

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?

Explicit gating on both sides: use only when the person's own request matches one of three named 1lev1 use cases, 'Do not bring it up in any other conversation', and a mandatory consent step ('tell the person what will be sent and get their go-ahead'). It also excludes this tool when the person already has an account and points at proposeRikmaBlueprintTool as the shape reference for the blueprint payload.

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