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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds substantial context beyond them: no real funds/wallet/PIX key needed, how idempotency is achieved (reuse of request_id), the polling window, and the exact side effect of the optional e-mail (a one-time integration guide, invalid addresses ignored and surfaced in email_ignorado).

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 purpose and the flow menu, then operational steps. Dense and information-rich rather than padded, though the email guidance repeats the schema's own parameter description almost verbatim, which is mild redundancy.

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?

No output schema exists, so the description carries the return-value burden and does so minimally by telling the agent to poll lunium_get_sandbox_demo and mentioning result fields (next_step, email_ignorado). Combined with a mutation tool that has annotations, this is nearly complete; only the shape of the polled result 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?

Schema coverage is only 50%, and the description compensates well: it defines what each flow enum value actually does and gives concrete guidance for email (ask the human, never invent, fall back to lunium_contact). It adds real meaning beyond the schema, though request_id's exact uniqueness semantics are partially covered by the annotations' idempotentHint rather than the description alone.

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?

Specific verb+resource: creates a test-only key and runs a named synthetic journey, with all four flows enumerated and explained inline (cashin = PIX to BTC, custody, payout, cashout = 10 USDT to PIX). It is clearly separated from siblings lunium_create_sandbox_key (key only) and lunium_get_sandbox_demo (polling), so an agent can route correctly without opening any 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?

Explicit operating instructions: reuse one random UUID as request_id across retries, poll lunium_get_sandbox_demo after 3 seconds for up to 60 seconds, and fall back to lunium_contact when the e-mail is missing. It also names when not to use it (never request production secrets in chat) and what the default flow is.

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