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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds the hard constraint w*h <= 10000 and the underlying GET /api/region call, which are real behavioral facts not present in structured fields. Undisclosed: what happens when the rectangle exceeds the pixel cap (error vs clamp) and any rate limiting on the wrapped endpoint.

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 purpose and size cap, then format semantics, then the coordinate system — no filler sentences and nothing repeated from annotations. The coordinate clause is densely packed into one line, which slightly hurts parseability but not content.

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 still explains the payload for both formats (base64 RGBA + empty/buyer/house runs with public display names; PNG image), which is what an agent needs to consume results. It leaves error/edge behavior unstated, notably rectangle-size violation handling and whether partial off-wall regions are clipped.

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 0%, so the description carries the full burden and does: x is left-to-right 0..999, y is top-to-bottom 0..999, w/h must satisfy the w*h <= 10000 product bound, and format's two enum values are explained with the default. It even gives the cell-index formula y*1000 + x, meaning not expressible in the JSON schema at all.

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 ('Pixels and owners of a rectangle'), names the two output formats, and pins the exact HTTP endpoint it wraps. An agent can distinguish this from wall_overview (whole-wall aggregate) and check_cells_available (availability probe) without opening a sibling schema.

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?

Explains the choice between the two formats with their contents — json yields base64 RGBA plus owner runs, png yields an image — and states json is the default, which is directly actionable. It stops short of routing the agent against siblings (e.g. use wall_overview for a coarse view, check_cells_available before buying) or stating when not to call it.

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