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

Annotations already declare this mutates non-destructively and is idempotent and openWorld, so the bar is lower. The description adds real value beyond that: it discloses the return contents (deposit address and exact amount) and that the result lives in the invoice payment attempt, revealing the side effect. Auth requirements aren't mentioned.

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?

A single dense sentence that front-loads the action and the key return info, with the usage condition trailing. Every clause earns its place; the parenthetical is slightly awkward but informative.

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 fills the gap by describing the returned deposit address and amount. Combined with annotations covering the safety profile, an agent has enough to call it correctly; only auth/permission context is absent.

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% and both params are documented (asset_id from get_invoice_payment_methods, invoice_id from create_invoice). The description adds no syntax or format meaning beyond the schema, so the baseline of 3 is correct.

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 ('chooses the coin for an invoice') and clarifies the return payload (deposit address + exact amount). It distinguishes the manual-payer flow from the pay_url flow, though it doesn't name the closest sibling get_invoice_payment_methods as the source of asset_id directly in prose.

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?

Explicitly says when to use it: 'when you pass the address to the payer yourself instead of pay_url.' That names the conditional and implicitly the alternative, leaving little inference. It doesn't discuss prerequisites or failure cases, keeping it just shy of a 5.

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