purchase_study

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

Annotations already declare destructive/open-world/idempotent, and the description adds value beyond them: it discloses the charge currency (USDC), that budgets are code-enforced, the required retry discipline for idempotency, and a recovery path for pending payments that avoids double-charging. These are non-obvious behaviors an agent must know before invoking.

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?

Four tight sentences, front-loaded with the core action, then the cost model, then the retry and recovery rules. 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 partially compensates by describing pending payment/launch response states and how to recover them. Missing is any statement of what a successful purchase returns or where scheduling/launch status is later observed (e.g., get_study_status).

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 coverage is 0%, so the description must carry the load. It clarifies idempotency_key semantics (reuse the original on retries) and implies study_id refers to the already-quoted study, but it does not document formats, constraints, or what makes a study_id valid.

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+resource ('Purchase and schedule the quoted study') and names the funding mechanism (locally configured wallet, USDC). It is clearly distinguishable from quote_study, create_study, and the read-only siblings.

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 operational guidance: reuse the original idempotency_key on every retry, and recover pending payment/launch states through this same tool rather than paying again. It does not explicitly state the prerequisite (that a quote must exist first) or name sibling alternatives, but the context is unambiguous.

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