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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description instead spends its budget on non-obvious behavior — that keyframe values and styles are deliberately excluded as unbounded, and that on a multi-page project the tree reflects only the ACTIVE page while content tools also target that page. The main omission is that it never says whether the returned tree is complete or truncated for very large projects, though the output schema carries the shape.

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?

It is front-loaded with the tool's identity ("Structural OVERVIEW … the table of contents") and every clause carries information rather than filler. However, the paragraph is very dense with nested parentheticals, and the critical routing guidance ("Start here, then call inspect_layers") sits at the tail rather than near the top where it would aid scanning.

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 shape needn't be restated, yet the description still supplies the semantics that a bare schema can't: what safe_area means and when it is null, what a hug text layer's geometry represents, what off_canvas:true signals, and what the pages block implies. Combined with the explicit next-step routing, an agent has everything needed to call this correctly and act on the result.

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?

There is a single parameter at 100% schema description coverage, so the schema already explains that projectId is an opaque v4 UUID from list_projects/create_project. The description adds nothing further about projectId — its page discussion implies the project is the one being inspected but never ties that to the parameter. Baseline 3 applies when the schema does all the 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?

The first clause names a specific verb and resource — a structural overview of the composition — and immediately enumerates what it returns (canvas size, duration, safe area, z-ordered layer tree, animation flags). It explicitly distinguishes itself from inspect_layers, which returns the bounded-detail view, so an agent can choose between them without opening either schema.

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 an explicit call order ("Start here, then call inspect_layers([elementId, …]) for full detail on the specific layers you'll change") and an explicit prohibition ("Don't guess keyframe/style values from this overview"). It also routes page-scoped work to select_page / add_page / delete_page / reorder_pages, naming the alternatives directly.

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