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

Annotations already declare it is a safe, idempotent read; the description goes further by disclosing the ranking engine, the seed-slot behavior of liked games (fill free slots after seeds; overflow listed in ignored), the 'disliked never come back' rule, the per-pick fields returned, and a coverage limit (adult-only explicit games not covered; filtering best effort). These are traits not derivable from the annotations.

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?

Purpose, source and sibling contrast are front-loaded, and nearly every clause carries operative detail. It is a single dense block that runs long, so an agent must parse carefully, but little is filler.

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 an output schema present, return values need not be explained, yet the description summarizes the pick fields anyway (similar_to, price, Deck status, year, reviews, imho.run URL, Steam URL, tool_url). Combined with filter guidance, exclusions and coverage caveats, nothing an agent needs to call this 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?

Schema coverage is 86%, so the structured field descriptions carry most of the load (baseline 3). The description adds real meaning for preferences ('read as Steam tags', any language, and the result reports which tags it inferred) and for the feedback semantics of liked/disliked, but does not restate filter syntax.

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?

States a specific verb+resource (Steam game recommendations seeded by 1-3 games), names the ranking source (imho.run's recommender) and the output shape. It explicitly contrasts with the sibling games_like, so an agent can select between them without opening either 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 explicit when-to-use conditions versus games_like (several named games, filters beyond free/co-op/Deck, natural-language descriptions of what the user wants) and explicit when-not cases (find_game_by_description for naming a game from a description, game_facts for single-game facts). The feedback-loop invocation pattern is also spelled out.

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