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

Annotations only supply readOnlyHint and openWorldHint, so the description carries most of the load. It adds real behavioral context beyond those: library scoping, the two seed modes, the default for `by` (look), and what other_titles actually changes about the result set. It omits credit cost of clips (left to the schema) and says nothing about default result counts or behavior when neither frame_ids nor image is supplied.

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?

Front-loaded with the core distinction and dense with useful detail; no filler sentences. It is somewhat run-on with nested parentheses and em-dash clauses, which makes the two seed modes slightly harder to parse than they need to be, but nothing is redundant.

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 17-parameter, zero-required, no-output-schema tool, the description conveys enough to select and call it: what the seeds are, how to express them, and what the main mode switch means. Remaining gaps are return shape and what happens with no seed, which are moderate rather than blocking given the read-only, search-style nature of the tool.

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?

With 17 params at 59% schema coverage, the description meaningfully fills gaps on the highest-ambiguity inputs: it defines each `by` value (look = composition/drawing/rendering, colour = palette, content = subject matter), explains the accepted URL and data: URL forms for `image`, and clarifies other_titles. It leaves many filters (limit, per_title, exclude_titles, nsfw, kind, year ranges) to the schema or to the cross-reference to search_animation_frames.

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 the verb and resource precisely ('more ANIMATION frames') and scopes it to the animation library only, immediately separating it from similar_commercial_shots, similar_commercials, and find_similar. The two seed mechanisms (frame ids from prior results, or an image) make the operation concrete enough that an agent can distinguish it from search_animation_frames without opening any 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 concrete triggering conditions: the user asks for 'more like #2', or supplies any image including generated frames, uploads, and sketches. It also points to search_animation_frames for shared filter semantics. It stops short of explicit when-not-to-use guidance or routing away from sibling tools when no seed exists.

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