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

Annotations only declare readOnlyHint and openWorldHint; the description adds the quota, the charged: false marker in the response, the sampleable: false fallback behavior, and an explicit prompt-injection warning that names and symbols in the result are data, not instructions. That is exactly the kind of context annotations cannot carry.

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?

Five short sentences, front-loaded with the core action and quota, then the parameter contract, then the exclusion and the safety note. Nothing is repeated and no sentence is filler.

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, yet the description still tells the agent the key return signal (charged: false) and how to treat result content safely. For a two-parameter forwarding tool, an agent has everything needed to invoke it correctly.

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 0% and the schema only names two required fields, so the description carries the full burden — and it does: 'tool' is a name drawn from cashboard_catalog, and 'arguments' is that tool's own input object. Both parameters are given meaning that the bare schema lacks.

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 mechanism: run one paid tool for free as a sample, with a hard quota. The proxy/forwarding nature is unambiguous and distinguishes it from every sibling (cashboard_catalog, cashboard_chain_pulse, etc.), which are direct data tools rather than a sample gateway.

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 operating constraints: up to 25 samples per address per UTC day, and tools whose catalog entry says sampleable: false have no sample — an explicit exclusion. It also points to cashboard_catalog as the source of valid tool names. It stops short of saying 'prefer the paid tool directly when you need more than 25 calls or non-sampleable tools', so the alternative path is only implied.

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