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

Annotations already declare readOnly, idempotent and non-destructive, so the remaining need is behavioural context, and the description supplies it well: a freshness window ('verified within the last 8 days'), the No-Match result code 'NO_MATCHES' with up to 3 relaxations and a re-callable retry, and the default 'content_rating_max' of teen. It does not state rate limits or result pagination, which keeps it below 5.

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 is front-loaded in the first clause, but the rest is a dense run-on that mixes result semantics, filter defaults, error handling, and client rendering and attribution rules. The output field is named 'similarity_reasons' at the start and 'match_reasons' later, which is an avoidable inconsistency an agent could trip over.

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 13-parameter discovery tool with an output schema and full annotations, the description covers the pieces the schema cannot: freshness, published and playable guarantees, the zero-result contract, relaxation retries and default rating filtering. Only the semantic meaning of most filter parameters is missing, which the enum values partially mitigate.

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 only 15% across 13 parameters, so the description needs to carry the explanation. It covers just three of them: include_listing_only, plays and the content_rating_max default. The other ten (mood, genre, limit, min_quality, inputs, players, difficulty, exclude_genres, session_length_max) are left entirely to short enum lists in the schema.

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 and resource ('games similar to an anchor game'), plus the ordering ('by similarity') and the per-item output field. This is unmistakably different from the sibling tools get_game, search_games, trending and random_game, since it is the only anchor-based recommendation path.

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 only implied: an agent must infer that this tool is for 'I liked game X, give me more like it' versus filter-based search_games. The description does provide useful in-tool decision rules ('plays=here or plays=developer_site picks one kind', 'listing-only games with include_listing_only=true'), but it never names an alternative or a when-not-to-use condition.

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