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

Annotations already cover the safety profile (readOnlyHint, openWorldHint), and the description adds real behavioral context beyond them: that the multiple signals are combined rather than treated as alternatives, and that results include studio, director, genres, themes, look, synopsis, poster, and the specific frames matched on a look search. It does not discuss ranking, scoring confidence, or what happens when signals conflict, which keeps it out of the top band.

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?

It is a single dense but front-loaded block: purpose first, then the enumeration of signals, then the return shape, with no filler sentences. The heavy parentheticals ("like: \"Akira\"", the look aside) make it slightly hard to scan, but each clause carries information.

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 15-parameter, multi-modal search tool with no output schema, the description does the important work: it explains every search mode, that modes combine, and what the response contains. The remaining gaps — ranking behavior, how relevance is weighted across combined signals, and default limit behavior — are minor but real for a tool this configurable.

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 73%, and the description adds meaningful framing on top: it explains that "a LOOK" can come via image or frame_ids (titles whose frames look like it), gives a natural-language example of the brief shape, and clarifies that genre/theme/style accept multiple comma-separated values meaning all. It leaves nsfw, exclude_titles, limit, and the year bounds to the schema, which is acceptable given their descriptions.

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 opens with a specific verb+resource ("Find animated SERIES and FILMS") and immediately scopes the corpus ("animation library only — mostly anime, plus Western animation"), which cleanly separates it from the commercials/shot siblings in the same family. It then enumerates the retrieval modes, so an agent knows exactly what kind of tool this is 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?

It gives clear context for how to call it: search by story brief, by a similar title, by a look (image or frame ids), and/or by genre/theme/style/studio/kind/year, with the explicit note that "Signals combine." What it lacks is exclusion or routing guidance — it never says when to prefer search_animation_frames, find_similar, or get_animation_title instead.

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