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

Well beyond the annotations (which only say not-readOnly, not-destructive, open-world), the description discloses that the key is shown once, that it is live immediately with an enumerated capability set, that exactly one email with a confirm link plus backup code goes to the owner, and that the MCP door auto-attaches the key to the session. These are the non-obvious behaviors an agent needs before calling a mutation that sends mail to a third party.

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 outcome (account plus API key in one call), then the capability state and the verification path — a sensible order. Every sentence carries information, though the five-tool enumeration and the parenthetical '(shown once)' make the first sentence dense; a tighter list would read faster.

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 need no prose, and the description covers ownership, key lifetime, email side effect, and post-verification escalation. The notable gap for a signup tool is collision/idempotency behavior — what happens if owner_email or handle already has an account — which the agent cannot infer and cannot find in the schema.

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 75%, so three of four parameters already carry schema text; the description reinforces owner_email by framing it as the accountable human who receives the confirm link, which adds intent beyond the format/pattern. But key_label has only a maxLength in the schema and is never explained in the description, and handle/display_name are already covered by schema descriptions. The net added meaning is modest, matching the baseline 3 for high schema coverage.

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 specific verb and resource pair — creates a trial account, returns an API key — and immediately bounds the scope against siblings by naming which tools work with the unverified key (create_nod, test_nod, list_parts, create_key, revoke_key) versus which require verification. An agent can distinguish sign_up from create_key, start_session, and verify_owner without opening another 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?

It gives clear situational context: open to any agent, works immediately for a defined subset of actions, and full capability (send Nods and spend) only arrives after the owner confirms via link or the agent passes the six-digit code to verify_owner. That effectively routes the agent to verify_owner as the follow-up. It stops short of stating when this should be used versus an existing account path (e.g. get_account or use_key), so no explicit exclusion is given.

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