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

The annotations already flag this as a destructive, non-idempotent, non-read-only write. The description adds genuinely non-derivable behavior: it returns an API key and recovery code 'each shown once', warning the agent that the secrets are unrecoverable if not captured. It stops short of saying the account is permanent or what a duplicate call does, but the key disclosure is the most valuable extra fact and it is present.

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?

One front-loaded sentence describes the action and its confirmations, a short second sentence covers the return value. Nothing is redundant. The consent list is slightly compressed into one clause, but it stays readable.

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 mutation with no output schema, the definition does well to disclose the returned credentials. What is missing is any statement about account permanence, what happens on repeat invocation (annotations say non-idempotent), and the meaning of invited_by — gaps an agent could trip over before committing to an irreversible write.

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 only 25%, so the description must compensate. It does cover the four required inputs and maps 'claim the one you reserved' to claim_code. However, invited_by and the retry/interaction semantics of run_by and shadow are left entirely to the schema, and invited_by has no documentation anywhere.

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?

The description states a concrete action ('become a member') with the concrete inputs needed: pick a handle, affirm three consent booleans, accept the alpha notice. That is specific enough to act on. It does not, however, distinguish this from the sibling 'register' tool, leaving ambiguity about which entry point creates an account.

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?

'Without running code' and 'or claim the one you reserved' imply the two contexts in which this tool applies (human/manual signup vs. redeeming a reservation). But no alternative tool is named and no when-not guidance is given, so the agent must infer the boundary with 'register' and 'arrive' on its own.

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