ground

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

The description discloses the internal steps (pixel-grounding, lidar lift, size check, waypoint snapping) and the output flags (committed, visible) that guide subsequent actions. It does not explicitly state side effects, but implies it is a computation tool that returns coordinates.

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 compact but packed with necessary details: purpose, input format, process, and conditional usage. It is front-loaded with the core action and provides examples and next steps without redundancy.

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 covers the input, process, and output usage including conditional logic based on committed and visible flags. It does not enumerate all error states, but the key behaviors are described. It leverages the output schema for detailed return structure.

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 description explains the 'query' parameter with concrete guidance: pass the object or place in the instruction's own words, and even provides an example. This fully clarifies the meaning beyond the bare string type.

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 states a specific action (ground a referring expression) and the resource (live camera + lidar), and explains the process in detail. It distinguishes itself from siblings by focusing on pixel-grounding of references rather than counting or parsing.

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 explains how to use the output (publish_xy for drive_to) and provides conditional guidance based on committed and visible flags. It doesn't explicitly name alternatives or when not to use it, but the context is clear enough for an agent to know when to call it.

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