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

Annotations declare destructiveHint=true and readOnlyHint=false; the description is consistent and adds real context on top — that deletes are the fix for a mis-drawn element, that ids must be sourced from napkin_boards_get, and how coordinate frames differ for slides vs sketches. It stops short of stating whether deletions are reversible or how many ops can be batched atomically.

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-loads the draw/create capability, then mutation, then the coordinate rules, then a compact example. Dense but each part carries information; the trailing citation instruction is short and actionable. Slightly heavy for a single description, but nothing is filler.

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 6-parameter mutation tool with no output schema, it covers the two things an agent would most likely get wrong — where to get shape ids and which coordinate space applies. It omits batching limits (maxItems 100) and the workspace-slug requirement noted in the schema, so slightly incomplete rather than fully self-contained.

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 100%, so the schema already documents parameters and the baseline is 3. The description goes beyond it with origin/coordinate-frame semantics (slide-local 0,0→960,540; board-relative for sketches), a worked example of an ellipse+arrow+text cluster, and the rule that ids come from napkin_boards_get.

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 specific verbs and resource: draws shapes/strokes/labels on a board, and via updates/deletes changes or removes existing shapes. Explicitly distinguishes itself from the read-side siblings napkin_boards_get and napkin_boards_view, so an agent can tell what this tool owns versus its neighbors.

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?

Gives concrete usage contexts ('diagram on a sketch, annotate a deck slide') and routes the agent to napkin_boards_get for ids and napkin_boards_view for the coordinate frame the renderer uses. It does not, however, explicitly rule out nearby draw-capable siblings such as napkin_diagrams_create or napkin_deck_compose, leaving some alternative-selection inference to the agent.

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