Paint: reference card

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description's 'in-server documentation, no round trip to GitHub' usefully reinforces the offline/local nature, but it says nothing about output shape or size of the returned reference. With annotations carrying the behavioral load, a 3 is appropriate.

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?

One framing sentence then a compact topic list; the purpose is front-loaded and no sentence is wasted. The parenthetical glosses double as both topic definitions and parameter documentation, which is efficient rather than redundant.

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 single-optional-parameter help tool with no output schema, the description supplies what an agent needs to decide whether to call it and which topic to request. It could be slightly stronger by hinting at the depth/format of the returned documentation, but nothing essential is missing.

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 must carry the parameter burden, and it does: each enum value is annotated with what it contains (ops = every operation and its fields, colors = formats and named palette, workflow = how to plan a drawing, examples = copy-paste batches). Only blend, filters, svg, and limits are named without elaboration, which is a minor gap at one optional, defaulted parameter.

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 plainly that this is in-server documentation and enumerates the exact topics available, so an agent immediately knows this is the reference/help surface rather than a drawing op. It is cleanly distinguishable from all 24 paint_* siblings (paint_line, paint_fill, etc.) that mutate the canvas.

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 topic list implicitly tells the agent which call to make for which need (e.g. 'workflow (how to plan a drawing)', 'examples (copy-paste batches)'), and 'no round trip to GitHub' signals when to prefer this over external lookup. There is no explicit when-not or preconditions statement, but for a help tool the routing is clear.

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