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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds real behavior the annotations cannot: query semantics ('every word of the query must match', i.e. AND matching), searchable fields including bilingual tags, the tier model (base free vs premium via pack), and the absence of a title_id scope. It does not disclose result caps or pagination, which matters for a search endpoint.

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 sentence with the primary purpose and the ref format front-loaded, followed by the field list and then search semantics. The nested parentheses make it slightly harder to scan and the tier explanation is only loosely relevant to invoking a search, but almost nothing is wasted.

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?

With no output schema, the description usefully enumerates what each result entry contains (ref, kind, style family, title, tags, capabilities, tier) and explains the tier vocabulary, which compensates well. The remaining gap is result volume — no indication of how many assets come back or whether results are ranked or truncated.

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 100%, so each parameter is already documented in the schema, and the baseline is 3. The description reinforces the filter axes ('filter by kind and style') and the AND-matching rule for query, but adds no new syntax, defaults, or accepted-value detail beyond what the schema already states.

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 gives a specific verb and resource ('Search the video studio's library of characters, scenes, props and music') and immediately scopes it as pre-made 'ready assets every studio has', which separates it from generate_* tools and from get_asset_bundle. It even states the output identity (a ref of the form lib:office-guy@1), so an agent knows exactly what it is retrieving.

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?

Usage is clear from context: entries are 'refs to put into a VideoSpec', and the closing 'takes no title_id' signals this is a global, cross-title lookup rather than a title-scoped read. It never explicitly names an alternative such as generate_image or get_asset_bundle or states when not to call it, so it stops short of full routing guidance.

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