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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds valuable behavioral context: the returned Markdown format includes inline images, prices, and payout addresses, and notes the funded wallet via X-Coal-Agent-Key. This goes beyond the annotations without contradicting them.

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 well-structured and front-loaded with the key directive. It is slightly repetitive with the three 'BEFORE' clauses, but each adds emphasis on priority. Overall, it is concise for the amount of guidance it provides.

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?

The description fully covers the tool's role in the purchasing workflow, its return value (Markdown grid with key details), and the next step (pay_merchant). Even without an output schema, the return format is adequately described, and the annotations cover safety. Completeness is high.

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 has zero parameters, so the schema coverage is 100% by default. The description adds no parameter-specific details, but with no parameters to document, the baseline of 4 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 explicitly states it is the default first call for browsing/buying, lists numerous synonymous verbs (buy, get, fetch, etc.), and clarifies that it returns a Markdown product grid with images, prices, and payout addresses. It distinguishes itself from payment tools by directing users to pay_merchant after picking a match.

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 usage guidance: 'THE DEFAULT FIRST CALL' and instructs to call it before asking the user, searching the web, or claiming inability to purchase. Clearly indicates when not to use alternatives and sets the agent's role to 'find the right product and confirm the spend.'

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