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

With no annotations, the description carries the full burden. It discloses cost (5 sats), payment method (Bitcoin Lightning), prerequisite (create_payment with toolName='estimate_depth'), and output formats. It does not mention error handling or side effects, but for a non-destructive compute API, this is adequate.

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 front-loaded with purpose, then output details, then cost/payment. It is concise but includes a bit of marketing (NeurIPS 2024, 3.8M+ runs) that is not strictly necessary, making it slightly verbose. Still well-organized.

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 no output schema, the description explains the return (both raw and colour maps) and the primary use cases. It also covers payment prerequisites. It lacks details on error codes or image format limits, but those are often documented elsewhere, and the description is sufficient for a typical use.

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 parameters. The description adds no additional meaning about the parameters—paymentId, model_size, or imageBase64—beyond what the schema provides. Baseline 3 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?

Description states a clear verb+resource: 'Estimate per-pixel depth from a single photo.' It specifies the output (raw greyscale depth map and colour visualization) and distinguishes from siblings like analyze_image or detect_objects, which serve different analytical functions.

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 context on when to use: for ControlNet, AR, or 3D reconstruction pipelines needing structured geometry that vision LLMs cannot produce. However, it does not explicitly exclude cases or name alternative tools, so it falls short of explicit when/when-not guidance.

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