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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false and openWorldHint=false, so the mutation profile is covered. The description adds that elements have configurable timing/placement and can be attached to measured world anchors, which is genuine context. It says nothing about what is returned (presumably an element id), whether duplicate adds stack, or what 'measured world anchors' requires of the caller.

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?

Two tight sentences with the capability statement front-loaded and the anchor caveat second. Nothing is wasted, but the brevity is partly achieved by omitting load-bearing detail, so it is efficient rather than exemplary.

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?

A 19-parameter, enum-heavy creation tool with no output schema needs substantially more than two sentences — at minimum what kind accepts beyond the category list, how start/end/at/box/emit combine for placement and emission, and how attach relates to world anchors. The description leaves an agent guessing across most of the schema.

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 5% across 19 parameters — only project_id is documented in the schema. The description gestures at three parameter families (timing, placement, attach) but never explains emit, count, colour vs palette, intensity, style, text, images, dissolve_embers, or the id/attach semantics. With coverage this low, the description had to compensate and largely does not.

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?

Names a specific verb plus a well-scoped resource ('adds a procedural light, particle, drawing, shape, pictogram or sprite element'), and the categories map onto the kind enum. It stops short of naming any sibling (e.g. add_vector_graphic, add_text, add_motion_graphic), so the agent must infer the boundary from the kind list alone.

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 and no exclusions. With siblings like add_vector_graphic, add_motion_graphic, add_overlay and add_stylize all plausibly overlapping, the description gives the agent nothing to route on; usage is only implied by the enumerated element categories.

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