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

Annotations already declare readOnlyHint, idempotentHint, closed-world and non-destructive, so safety is covered. The description adds useful context beyond that: it discloses that the payload is prose guidance organized by topic and hints at the kind of content each topic yields (durations, curves, springs, loop/shaders, converting library examples). It does not say how large the returned guidance is or whether multiple topics are returned together, which is a minor remaining gap.

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?

Purpose and the when-to-read instruction are front-loaded and the topic list is dense but every parenthetical disambiguates a value the agent must choose between. The single long sentence with a nested parenthetical is slightly heavy to parse, but no sentence 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 single-parameter, read-only documentation fetch with no output schema, the description covers purpose, topic selection, and when to call it. The only omissions are return shape (prose vs. structured) and volume, which are low-cost gaps given full schema coverage and clear annotations.

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% and the enum names are self-describing, so baseline would be 3. The description earns a step above by disambiguating non-obvious values — principles as "whether to animate at all", timing as durations/curves/springs, adapting as "turning a library example into project code" — which meaning is not present in the bare enum strings.

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 and resource ("Get Subframe's guidance for designing motion") and immediately scopes it by topic with a full enumeration of the available topics. The closing clause ("not only library examples") implicitly separates it from the sibling example-lookup tools, so an agent can tell what this returns without opening the 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?

"Read the relevant topics before designing, adapting or reviewing any animation" gives a clear trigger condition covering the main workflows. It does not explicitly name or exclude a sibling alternative, but the "not only library examples" phrasing signals the complement relationship to the example tools, which is enough context to choose correctly.

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