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

Annotations only say the call is a non-read-only, non-idempotent, open-world write. The description adds the material behavior annotations cannot express: it sends an email, it is a two-step flow, the first call returns the key terms, the terms must be explicitly accepted, and it is 'Free to call' (no charge incurred at this step).

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?

The purpose and the step-1-of-2 framing are front-loaded, followed by the pre-call checklist, which is the right order. The embedded pricing ladder is the only bulk; it is useful but could be compressed or deferred to the plan schema. Little else is wasted.

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 6-parameter, non-idempotent onboarding write with an output schema, everything an agent needs to call it correctly is present: prerequisites, the terms-acceptance mechanic, what the call returns to the user, and the handoff to confirm_signup.

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 the schema already explains each field; the description nonetheless adds business meaning the schema lacks — the four plan tiers with prices and the yearly = two-months-free, one-time, never-auto-renewing billing model, plus the card-or-crypto prompt. It does not restate plan/billing/crypto syntax, but the pricing context is genuinely additive.

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 names a specific verb and resource ('Create a CapitalSnitch account — or sign back in') and explicitly frames itself as 'Step 1 of 2: emails the user a 6-digit code,' which separates it cleanly from confirm_signup. An agent can route between the two without opening either 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 states what to do before calling (ask about plan, collect payment preference, show key terms), what happens after (ask for the code, then call confirm_signup(email, code)), and the exact gating rule for user_accepted_terms ('call once without user_accepted_terms to get them... only after an explicit yes'). Alternatives and sequencing are unambiguous.

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