png

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

The annotations already declare readOnlyHint=false and destructiveHint=true, so the caller knows this writes and can destroy data, while openWorldHint=false and idempotentHint=true say it stays local and repeats safely. The description adds nothing beyond that: it never says the output file is overwritten if it exists, whether the current viewport/camera state is what gets captured, or that the ray-tracing path is slower. For a destructive write tool the description is essentially silent on the behavior an agent most needs.

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?

At four words there is nothing to trim, but this is brevity through omission rather than disciplined editing. The single sentence is front-loaded by default, but it does not carry the information load the tool requires.

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?

An output schema exists, so return values need not be explained, and with only two parameters the surface is small. Still, for a destructive file-writing tool with a sibling PNG variant and a `ray` option, the definition omits overwrite behavior, viewport-state dependency, and the choice against `mpng` — all things the agent needs to invoke it correctly.

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 100%, with both `filename` (output path) and `options` (width, height, dpi, ray) documented in the schema itself. The description contributes no additional meaning about the `options` string syntax or how `ray` changes the result. The baseline of 3 applies when the schema already does this work.

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?

"Saves a PNG image" gives a verb and a resource, so the basic action is clear, but it adds nothing the tool name "png" does not already imply. It does not distinguish this from the closely related sibling `mpng` (likely movie/multi-frame PNG) or from `print_export`/`render`, leaving the agent to guess which output tool is which.

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?

There is no when-to-use guidance at all: no mention of when to prefer `png` over `mpng`, `print_export`, or `render`, and no note on prerequisites such as a loaded scene or current viewport state. The agent must infer everything from the name and the surrounding tool list.

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