ae_addShapeLayer

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is covered and the description only needs to add context. It does add some: the default comp-center behavior, the purpose of trimPaths ('for write-on animation') and the star innerRatio default — but it never says the new layer is appended to the active comp or what identifying info (layer index/name) comes back.

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 front-loaded sentence pair, no filler, and the host app plus the shape vocabulary come first. The em-dash nesting makes it dense to parse but nothing is 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 16-parameter creation tool with no output schema, the description covers the creative semantics but leaves a real gap: it never says what the call returns, so an agent has no documented handle to feed into ae_setTransform or ae_duplicateLayer afterwards. Safety and open-world behavior are covered by annotations, which limits the damage.

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?

With 44% schema coverage across 16 parameters the description must carry weight, and it does pick the highest-risk ambiguities: 'position = layer center (default comp center)' fixes a convention the schema leaves undefined, and the path point format/relative-to-center note disambiguates pathPoints. Still, ten-plus parameters (name, closed, lineCap, opacity, stroke, strokeWidth, cornerRadius) get no semantic explanation anywhere.

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?

Opens with a specific verb+resource tied to a host app ('After Effects: add a vector shape layer') and enumerates the six supported shape kinds, so an agent can tell it apart from ae_addTextLayer, ae_addSolid and ai_addShape without opening a schema. It stops short of naming the nearest sibling (ae_shapesFromVector), which is the one case where the boundary is genuinely ambiguous.

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?

Usage is only implied by the verb 'add' — there is no statement of when to prefer this over ae_shapesFromVector (converting existing vector art) or ae_addSolid. No prerequisites (open comp, active comp requirement) are stated beyond the schema note about omitting compositionName.

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