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

Annotations declare a non-read-only, open-world, non-idempotent operation, and the description goes well beyond them: exact cost ($1.00), payment rail (x402/USDC on Base), that an API key is returned, how to present it (Bearer header or params._meta), and the credit accounting rule 'each successful call uses one credit; failed calls are free.' This is exactly the extra behavioral context annotations cannot convey.

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?

Three sentences, each carrying distinct payload: what is bought, what is returned and how to use it, and the credit-consumption rule. Cost and payment method are front-loaded, with no 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?

With no output schema, the description still tells the agent what comes back (an API key) and precisely how to consume it on sibling tools, plus the billing semantics. For a zero-parameter purchase tool this covers everything needed to call 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?

The tool takes zero input parameters, so there is nothing for the description to disambiguate beyond what the empty schema shows. Baseline 4 is appropriate; no parameter meaning is missing.

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 with exact scope and price: 'Buy 20 paid calls for $1.00 in one x402 payment (USDC on Base).' An agent can immediately distinguish this purchase tool from the read/write siblings (atlas_kit, atlas_search, atlas_lint) without opening any schema.

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 explains the payoff of buying the pack: use the returned key 'on atlas_kit or atlas_draft instead of paying per call,' which implies when this is preferable to per-call payment. It stops short of an explicit when-not (e.g., don't buy if you only need one call), so it is clear context without full exclusion guidance.

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