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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true): it discloses that requests are manually reviewed and paid, that the first address is permanently pinned so later requests can only go there, that addresses are screened against the OFAC sanctions list, and that prerequisites can block the call. These are non-obvious consequences an agent could not infer from structured fields.

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 core action, then layers preconditions, sanctions screening, and first-request fields in a logical order; no sentence is filler. It is dense but slightly list-like in the back half, with several policy sentences that could be tightened.

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?

With no output schema, the description correctly explains the post-call lifecycle (manual review, then marked paid with a transaction hash), so the agent knows the call is asynchronous rather than returning funds immediately. For a one-shot withdrawal with 100% schema coverage, this is close to complete; only a note on what happens to a pinned address if it is rejected or on retry behavior is missing.

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 100%, so the baseline is 3; the description still adds meaning by explaining the address pinning rule (why address is optional after the first call) and by grouping legal_name, country, and us_person as a one-time operator self-certification that must accompany the first request. It does not add format detail beyond the schema, but the cross-parameter relationship is genuine added value.

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?

States a specific verb and resource ("Requests a withdrawal of your whole available referral balance") plus currency (USDT) and network (TRC20), and clarifies that the entire balance is withdrawn rather than a caller-specified amount. An agent can distinguish this from all listed siblings (account_status, buy_plan, plans, etc.) without opening the 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?

Gives concrete usage conditions: the tool is closed while the plan payment is overdue, service partner earnings unlock 14 days after the client pays, and the first request additionally requires the tax self-certification. It does not name a sibling alternative, and the only redirection ("change it in the cabinet") points outside the tool set, so it stops short of full when/when-not routing.

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