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

Annotations already declare readOnly/idempotent/non-destructive, so the added value here is "One call, no generation" — signalling a cheap precomputed read rather than an expensive synthesis step. It does not discuss size, latency, or what happens when no taste data exists.

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 what you get back, then the usage trigger. The long enumeration of taste facets is dense but each item informs the agent what is available; still, it could be trimmed without loss.

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?

No output schema exists, and the description compensates by enumerating the returned facets and the Taste Portrait essence, including the conditional "when they have one". An agent can decide and call correctly with nothing else needed.

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% and there is a single optional enum-array parameter, so the schema carries full meaning. The phrase "across everything they read, watch, listen to and play" loosely echoes the media types but never references the media_types filter or its omit-for-all behavior.

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?

Clear verb+resource (their taste) with an explicit content inventory — loved items, returning creators, genres, in-progress, finished, misses, plus Taste Portrait essence. That inventory implicitly separates it from get_taste_portrait and get_stats, though no sibling is named directly.

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?

"Use it whenever knowing their taste would make your answer fit them better, including outside media (a trip, a gift, a reading list for a project)" gives explicit positive triggers with concrete examples beyond the media domain. It lacks any when-not guidance or named alternatives such as get_taste_portrait or get_signals for narrower needs.

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