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

The description goes far beyond the sparse annotations, disclosing that the charge happens off-session with no confirmation step, that the server sets the price, and that every successful call is a separate charge. It enumerates machine-readable error codes with precise money-movement semantics (e.g., 'purchase_incomplete' means the card WAS charged but crediting failed). This is exemplary behavioral disclosure for a high-stakes financial tool.

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 long, but every sentence earns its place for a money-spending operation: the critical warning is front-loaded, the purchase range and pricing are compact, and the error-code details are dense with actionable information. No filler is present, and the structure leads with the most safety-critical fact before moving to operational details.

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?

Despite having no output schema, the description tells the agent what outcomes to expect, how to interpret unusual cases, and how to verify completion via list_credit_transactions. It covers success paths implicitly, failure modes explicitly, and retry protocol thoroughly. For a mutating tool with real-world money movement, this is complete enough to call correctly and safely.

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?

The single parameter 'credits' is fully described in the schema with the same range (1,000–10,000) and the same meaning ('prospect credits'). The tool description adds pricing-tier context and the note that the server prices the charge, which is useful but not essential to understanding the parameter itself. With 100% schema coverage, the baseline of 3 is appropriate.

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 states a precise action: buying 1,000–10,000 prospect credits, while clearly flagging that this charges real money. It is strongly differentiated from siblings like get_credit_balance and list_credit_transactions by emphasizing that every successful call creates a new charge. The opening warning 'SPENDS REAL MONEY' leaves no ambiguity about the tool's function.

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 provides explicit when-to-use and when-not-to-use guidance, especially around retry behavior: do NOT retry on 'purchase_incomplete', safe to retry on 'temporarily_unavailable', and 'credits_free' means there is nothing to buy. It also names list_credit_transactions as the verification alternative for timeouts, dropped connections, or 'purchase_unconfirmed' outcomes, giving the agent a concrete routing path.

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