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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description adds the downstream contract ('the names and ids it returns are what style_clip, add_to_clip and edit_clip take') and that each item carries a premium flag, which the annotations cannot express. 'Free and read only' merely restates the annotations, and no error or truncation behavior is described, so it falls short of a 5.

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?

The triggering use case is front-loaded, followed by the kind enumeration, then parameter semantics, then exclusions — a logical order with little waste. The kind list is a long run-on and 'Free and read only' duplicates the annotations, and the raw line-wrapping hurts scanability, keeping it from a 5.

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 structure needn't be explained, yet the description still notes the premium flag and that returned ids feed sibling style/add/edit tools. For a three-parameter read-only browse tool, an agent has everything needed to select and call it correctly.

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 0% and the schema has no enum on 'kind', so the description carries the full burden — and it does: all fifteen kind values are listed with parenthetical explanations (e.g. 'text_styles (titles, lower thirds, subscribe buttons)', 'templates (the user's saved styles and the starters)'). It also defines query semantics ('narrows by a word from a name or group') and the limit ceiling (300, default 100), fully compensating for the bare schema.

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 description states the resource precisely (a catalog of editor assets) and the user intent that triggers it, with concrete example phrasings ('which caption styles are there', 'what fonts'). It also enumerates the exact catalog kinds, so an agent can distinguish this browse tool from style_clip, add_to_clip and edit_clip 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?

Explicit 'Use this when the user wants to know what the editor offers before changing a clip' gives the positive trigger, and the 'Not for:' block names three concrete alternatives (style_clip, add_to_clip, edit_clip) plus two other lookalikes (list_clips, list_clipping_presets). Both when-to-use and when-not-to-use are covered, leaving nothing to inference.

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