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

With no annotations, the description carries the full burden and does well: it discloses cost (5 sats per image), payment mechanism (Bitcoin Lightning, pay per request, no API key/signup), the required create_payment prerequisite, and that both raw greyscale and color visualization outputs are returned. It omits latency/timeout behavior and input size limits, but covers the major behavioral traits.

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?

Front-loaded with the core action and resource, then efficient supporting details about outputs, cost, and prerequisites. Slightly dense with promotional asides ('3.8M+ runs', 'Structured geometry a vision LLM cannot produce'), but every sentence contributes relevant information.

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 correctly fills the gap by explaining both return values (raw greyscale depth map and color visualization) and the payment workflow. It is nearly complete for a paid, 4-parameter tool; only latency/timeout expectations are left implicit via the schema's resultKey hint.

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 description coverage is 100%, so the schema already documents paymentId, resultKey, model_size, and imageBase64. The description adds no additional parameter meaning beyond what the schema provides; baseline 3 is appropriate when the schema does the heavy lifting.

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: 'Estimate per-pixel depth from a single photo', naming the model (Depth Anything V2) and the exact output (per-pixel depth map). This clearly distinguishes it from siblings like generate_3d_model or analyze_image, which produce different artifacts.

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 clear usage context: 'what a ControlNet, AR or 3D reconstruction pipeline consumes' and 'Structured geometry a vision LLM cannot produce' implies when this beats generic vision tools. The payment prerequisite (create_payment with toolName='estimate_depth') is explicit, but there is no explicit exclusion or named alternative sibling tool.

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