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

Annotation Contradiction: the description says the balance is credited and the tool tops up the balance, which is a mutating operation, while the annotations declare readOnlyHint=true. This is a direct contradiction and is very misleading for an agent deciding whether the tool changes state.

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 description is front-loaded with the purposehare, then gives prerequisites, the exact HTTP flow, and an explicit alternative. It is dense but each sentence earns its place; the embedded JSON example makes it slightly less scannable.

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?

The description covers the prerequisite credential, the invocation flow including the HTTP 402 challenge, the immediate crediting behavior, and the fallback tool for agents without credentials. Given the simple one-parameter schema and no output schema, this is operationally 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 description coverage is 100% and there is only one parameter, amount_usd, already documented with min/max and meaning. The description reinforces amount_usd with a POST example, but adds little substantive semantic information 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?

The description leads with a specific verb and resource: 'Tops up the ProxyCove balance by paying yourself.' It also differentiates from the sibling create_topup by explicitly contrasting the no-human flow with the link-to-human flow.

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 states when to use this tool: when the agent has a machine payment credential (MPP / Shared Payment Token). It explicitly names the alternative, create_topup, and the condition for choosing it: no payment credential.

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