canvas_size

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

Annotations already declare this is a non-read-only, non-destructive mutation, and the description adds useful behavioral detail that negative margin values cut pixels. It does not cover persistence (save default true), backend auto/live/batch behavior, or reversibility — though save and backend are documented in the schema, so the gap is moderate rather than severe. No contradiction with destructiveHint=false.

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?

A single dense sentence with zero filler, and the core behavior ('without scaling pixels') is front-loaded before the parameter modes. It could be marginally clearer about whether the two modes are mutually exclusive, but it earns its length.

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 an 11-parameter tool at 27% schema coverage with no output schema and no descriptive annotations, the description covers the core spatial parameters adequately but is silent on trimOutside, anchor value effects, and the live-vs-batch save implications. Adequate but with clear gaps for a tool this size.

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 27%, so the description carries real weight and it does explain left/top/right/bottom direction semantics and that negatives cut, plus the width/height+anchor mode. It leaves anchor selection meaning, trimOutside, and whether the two modes can be combined unexplained.

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 (grows/shrinks) and resource (canvas) plus the key differentiator 'without scaling pixels', which implicitly separates it from resize_sprite. It doesn't name the sibling explicitly, but an agent can distinguish it.

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 'either margins ... or width/height with an anchor' clause gives useful mode-selection context for the two ways to call it. However there is no explicit guidance on when to choose canvas_size over crop_sprite, resize_sprite, or trimOutside, so usage is only implied.

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