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

With no annotations, the description carries the full burden and does substantial work: it discloses exclusions (keyframe values/styles are unbounded), the active-page behavior, and the exact pages block shape. However, it never explicitly states the call is read-only, and the input schema's projectId description claims this call 'mutates' the project — an inconsistency the tool description does not preempt.

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?

All five sentences earn their place: core scope and return content first, exclusions second, multi-page caveat third, then routing to inspect_layers and a final guardrail. Dense but every clause carries signal; 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?

No output schema exists, and the description compensates by detailing the return values (canvas, duration, z-ordered tree fields, pages block) and the multi-page edge case. The only gap is the unresolved read-only question: the schema's 'mutates' wording plus a missing explicit no-side-effects statement leaves slight ambiguity for a tool that is clearly an overview.

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 baseline of 3 applies even though the description adds no parameter-specific syntax. The description's multi-page note indirectly clarifies what projectId selects (the active page), but the schema text itself is misleading: 'Selects which existing project this call mutates' is wrong for a read-only overview tool.

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 a specific verb+resource: a structural overview / table of contents of the composition, enumerating exactly what it returns (canvas size, duration, backdrop summary, z-ordered layer tree with elementId, type, geometry, animated properties). It explicitly differentiates itself from inspect_layers and the page-management siblings, so an agent can select it correctly without opening schemas.

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 explicit sequencing: 'Start here, then call inspect_layers' for full detail on the layers to change. It also names the exact alternatives for page management (select_page, add_page, delete_page, reorder_pages) and warns 'Don't guess keyframe/style values from this overview,' covering both when-to-use and when-not-to-use.

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