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

With no annotations provided, the description carries the full burden. It discloses cost ($0.10), determinism, technical mesh details (marching-columns, self-made font, LCG grain), and output formats. It also clarifies the payment flow. However, it omits the payment destination (e.g., where to send USDC) and what happens after payment—whether output is returned as files or URLs. These gaps prevent a perfect score.

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 extremely concise—a single sentence that front-loads the most critical information (cost and purpose) and packs in all necessary details: determinism, output formats, mesh technique, font, and payment instructions. No wasted words. The structure is effective for quick parsing.

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 complexity of a paid 3D generation tool with payment, parameters, and output, the description is incomplete. It fails to specify where to send payment (the USDC address or payTo address mentioned in the schema), how the output is delivered (download link, direct binary?), and what happens if payment fails. The schema mentions 'payTo' in the payment_tx description, but the tool description doesn't explain how to obtain that address. These gaps hinder an agent from executing the tool 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?

Schema coverage is 100%, so the schema already documents all three parameters. The description adds context about payment_tx being required ('Pay first, then pass payment_tx') and seed being optional, but this contradicts the schema's required list (only 'word' is required). This creates ambiguity about whether payment_tx is mandatory. The description adds value by explaining the payment flow, but the inconsistency with the schema lowers the score.

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 the tool's function: 'FORGE: deterministic 3D relief medallion of your word' with specific output formats (GLB+OBJ). This distinguishes it from siblings like khotem_seal or khotem_med, which likely have different purposes. The verb 'forge' is specific and the resource is a medallion, making the purpose unambiguous.

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 usage steps: 'Pay first, then pass payment_tx + word (+seed).' This tells the agent the required sequence and prerequisites. It doesn't explicitly mention when not to use this tool or alternatives, but the unique paid 3D medallion generation clearly separates it from other khotem_* tools. The payment-first instruction is a strong usage guideline.

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