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

With no annotations, the description does substantial work: it discloses that no signup or card is needed, that credits are credited automatically after payment confirms, and that the amount is deliberately unique so payments can be matched. Gaps remain around invoice expiry and whether repeated calls create multiple invoices, but the core behavior is disclosed.

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 is front-loaded in the first sentence, which is good. However, the closing sentence ('Next: pay the exact amount shown, then poll deposit_status') largely repeats the earlier 'Pay the exact amount and address in the returned uri' and 'Poll deposit_status' statements, so a meaningful share of the text is redundant.

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 two-required-parameter creation tool with no output schema, the description covers the essential lifecycle: what is created, how to pay, and when credits land. It even references the returned uri, partially compensating for the missing output schema. Missing invoice expiry and duplicate-call semantics keep it short of complete.

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 usd, rail, and account_key are already fully documented in the schema, establishing a baseline of 3. The description adds a little meaning — that the exact amount in the returned uri must be paid — but nothing about parameter syntax or constraints beyond the schema.

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 concrete verb and resource ('Create a crypto deposit invoice to buy credits') and immediately scopes it to the two supported rails (USDC on Base, BTC on-chain). This is clearly distinguishable from siblings like get_balance or deposit_status, which appear in the same workflow.

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?

The description gives the full workflow sequence — create the invoice, pay the exact amount in the returned uri, then poll deposit_status — which tells the agent exactly what to do next. It does not explicitly state exclusions or when to prefer an alternative over this tool, but the sequencing against deposit_status is clear.

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