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

Beyond the read-only/idempotent annotations, it discloses non-obvious behavior: "No account required," that provider filters apply in the requested country while "country alone does not filter availability," how dislikes and exclusions differ in effect, and that qualities_applied reveals whether mood text affected ranking. These are operating facts an agent cannot infer from annotations alone.

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 use cases and routing before mechanics, which is the right order. Some sentences are telegraphic ("Dislikes adjust comparable affinities; exclusions hide exact titles") and the return-field enumeration duplicates the output schema, costing a little density.

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, constraint-heavy recommendation tool it covers the full picture: prerequisites, sibling routing, input combination, dislike/exclusion semantics, availability caveats, and no-account access. Nothing an agent needs in order to call or interpret it correctly is missing.

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?

Top-level schema coverage reads 0% and the request object has no own description, so the prose must carry the load; it does explain seed_ids (positive references), avoid_seed_ids vs exclude_ids, intent's evidence emphasis, and the limit-as-shortlist meaning. It stops short of covering the many nested constraint fields (variety, offer_types, runtime caps), which the schema documents inline instead.

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?

Opens with concrete use cases ("Find movies like X, shows to watch after Y, or alternatives when someone liked one title but disliked another") that pin down a specific verb and resource. It clearly separates itself from search_titles (name resolution) and get_charts (mood-only discovery), so an agent can pick it without opening a sibling 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 an explicit prerequisite workflow ("Resolve names with search_titles first") and an explicit when-not rule ("For open-ended or mood-only discovery without reference titles, use get_charts"), with the reason supplied. It also states the input combination to pass: positive and disliked reference IDs plus desired qualities.

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