Buy credits (returns a payment link or crypto invoice)

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

With no annotations, the description fully discloses behavioral traits: it does NOT complete payment, returns a payment link/address, specifies the human requirement for stripe, and explains that credits are added automatically once crypto payment confirms. This goes beyond basic purpose to detail the exact transaction flow and autonomy levels.

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 longer than two sentences, but it is well-structured with bullet points and every sentence carries functional weight. It avoids fluff while covering method-specific behavior, return values, and prerequisites.

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?

Given the tool's complexity (two payment methods with different requirements), the description is remarkably complete. It covers prerequisites, what is returned for each method, who can complete the payment, and follow-up behavior (automatic credit addition), leaving no critical gaps even without an output schema.

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 schema already documents all parameters with descriptions and enum values, so the bar is higher. The description adds valuable interaction semantics, such as how method 'crypto' with a currency returns a raw wallet address and amount. This enriches the schema without redundancy, justifying a score above baseline.

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 clearly states 'Start a purchase of a credit package and return a way to pay', identifying the specific action and resource. It distinguishes itself from sibling tools like get_credits (checking balance) and get_packages (listing packages) by explaining the purchase initiation purpose.

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?

Provides explicit when-to-use guidance: 'Prefer crypto for fully autonomous top-ups' and instructs to 'Get a package id from get_packages first'. It also gives an exclusion by warning that an agent cannot finish a card payment on its own, thus steering agents toward the crypto method when needed.

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