scan_area

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

With no annotations, the description carries the full burden and mostly succeeds: it discloses row order (north to south), unexplored-tile representation ('?'), and symbol meanings (uppercase, lowercase, @). It doesn't state whether the operation is purely read-only, but the passive 'scan' framing and emphasis on output format cover the most important behavior.

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?

Three short sentences with no filler, front-loading the core output ('ASCII tile grid of a square area') and then adding distinct facts: orientation, unexplored marker, and legend. Every sentence earns its place.

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 output format and legend are well covered, and an output schema exists so return values don't need explanation. However, the description leaves x/y semantics and the geometric relationship between radius and grid size unexplained, and offers no comparison to observation siblings, so an agent may still guess at input meaning.

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 only 33% (only radius is described), and the description adds no meaning for x or y: whether they are coordinates, whether null means 'current position', or how they relate to the square area. The description also doesn't reinforce the radius half-width relationship beyond what the schema already says.

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 defines a concrete output: an ASCII tile grid with one character per tile, row orientation, and symbol legend, making the tool's function clear. It doesn't use an explicit verb like 'scan' in the description and doesn't explicitly distinguish itself from look_around, but the output format is distinctive enough to identify its purpose.

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?

No guidance is given on when to use scan_area versus look_around, find_buildable_area, or other observation tools. The description only explains what the output looks like, not the situations that call for it or when a sibling would be preferred.

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