Create animation card

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

With no annotations, the description carries the full burden (baseline 3). It goes beyond by disclosing: scenes play sequentially in a 16:9 stage with controls, everything is procedurally generated (text, SVG shapes, CSS animation) with no external assets, and shows how to handle variations via per-scene transitions/durations. It misses some edge cases (e.g., what happens if scenes is empty – though schema enforces minItems 1), but the disclosed behavioral traits are rich and accurate.

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 description is substantial but every sentence earns its place, covering what, why, and how to compose scenes. It could arguably be front-loaded more (the key 'when to use' is first, which is good). Minor deduction for density - an agent might need to parse carefully - but no fluff.

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?

Given the tool's complexity (nested scenes, transitions, shapes, charts) and the rich schema, the description does an excellent job of tying it together. It explains the animation model (sequential scenes, transitions), provides patterns (title reveal, chart zoom), and even implies limits (no external assets means you can't rely on images). Not a 5 because it doesn't explicitly document error cases or fallbacks, but for the complexity it covers the essentials well.

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 63%, so the schema itself documents most parameters. The description adds value by implying how scenes (structure of shapes, bullets, chart) relate to the animation, and clarifies the 'no external assets' constraint that affects how to fill scene content. However, it does not directly explain the semantics of properties like durationMs, loop, or autoplay beyond what the schema already states, so it doesn't fully bridge the 37% gap.

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 uses a specific verb ('Render'), identifies the resource (a short animated clip as a card), and clearly distinguishes when to use it: when no direct video URL exists but motion would communicate better. It also differentiates from siblings like create_video_card by emphasizing generated content (text, SVG, CSS) over external assets, which is a strong differentiator visible in the sibling list.

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?

The first sentence explicitly states the primary use case and contrasts with the alternative ('when no direct video URL exists'). It also gives composition guidance ('Compose classic clip patterns and vary them per conversation') and lists concrete examples that heavily imply when to use this over a static card. While it doesn't name a specific sibling, the 'no direct video URL' contrast with create_video_card is an explicit exclusion condition.

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