read_pixels

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 the return shape, the '.' = transparent convention, that omitting `layer` yields the flattened frame, and that the region is capped at 128x128. It does not state whether the call itself is side-effect free or what happens if the region exceeds the cap.

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 tight sentences with no filler, and the size cap is stated compactly. The opening fragment ('Pixels as a character map: {...}') prioritizes return format over purpose, which is mildly awkward as a lead but still efficient.

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?

For a 4-parameter read tool with no output schema, the description compensates by inlining the exact return structure and the transparency convention, which is the key missing piece. The remaining gap is `frame` semantics for multi-frame sprites, which matters given siblings like `check_animation` and `tween_poses`.

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 0%, so the description must compensate and only partly does: it explains `layer` (flattened frame when absent) and `region` (128x128 cap), but `frame` (default 1) and `path` are never given meaning, format, or numbering conventions. Two of four parameters remain purely schema-derived.

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 conveys a specific operation on a specific resource: reading pixels and returning them as a character map, with the flattened-frame behavior when `layer` is omitted. It is distinguishable from write-oriented siblings (`apply`, `pixelize`) and from `map`-op writes, though the verb 'read' only appears mid-sentence rather than being front-loaded.

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?

It sketches a concrete workflow ('edit the rows and send them back with the map op: a read-edit-write round trip'), which tells the agent how the output is meant to be consumed. However, it never compares against the many sibling inspection tools (`view`, `sprite_info`, `compare`, `export`) or states when not to use this instead.

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