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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so the safety profile is covered; the description adds real behavioral detail beyond that: up to twelve candidates, what each candidate carries, that general similarity sets the neighborhood while intent shifts evidence emphasis, that dislikes adjust affinities versus exclusions hiding exact titles, and that qualities_applied reveals whether mood text influenced ranking. It stops short of describing pagination or latency, but for a read-only recommendation call this is substantial added context.

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 use case, then prerequisites, then return shape, then semantics — a sensible order with no filler sentences. Some sentences are heavy with semicolon-joined clauses ('General similarity supplies the neighborhood; intent selects the supporting evidence emphasis'), which trades readability for density, so it is efficient but not maximally clean.

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 nested-request tool with constrained IDs, country/provider interactions, and several sibling alternatives, the description covers routing, key parameter relationships, and the return payload. With an output schema present it does not need to enumerate return fields exhaustively, and what it does say about candidates and qualities_applied is sufficient for correct invocation.

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?

The description explains the semantic division between positive seeds, disliked seeds, and exclusions ('Dislikes adjust comparable affinities; exclusions hide exact titles') and clarifies that qualities express the desired experience rather than saved taste. Unmentioned fields (kind, variety, genres, languages, offer_types) are left to the schema, and because the reported coverage signal is low those remain partly undocumented, which keeps this from a 5.

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 opening sentence gives concrete verb+resource phrasing with three recognizable use cases: 'Find movies like X, shows to watch after Y, or alternatives when someone liked one title but disliked another.' It explicitly routes to siblings ('Resolve names with search_titles first', 'use get_charts first'), so an agent can distinguish it from search_titles, get_charts, and recommend_for_me 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 names prerequisites (resolve names with search_titles first) and a clear alternative path (get_charts for open-ended or mood-only starts). It also states when constraints do and do not take effect ('Provider filters apply in the requested country; country alone does not filter availability'), which is exactly the kind of boundary guidance that prevents misuse.

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