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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's job is to add behavior — and it does: it discloses the weighting scheme behind the ranking and guarantees determinism ('the same game always gets the same answer'). It doesn't state how many results come back by default or what happens when a game has no similar matches, but the added context is genuinely useful.

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?

Three short sentences, each earning its place: what it returns, how it scores, and how it is deterministic, followed by the filter hint. The core purpose is front-loaded and there is no 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?

For an eight-parameter read tool with a fully documented schema and no output schema, the description covers purpose, ranking logic, determinism, and filter reuse — enough to call it correctly. The one gap is that with no output schema, it never hints at the shape of the result list (fields per similar game, whether a similarity score is included).

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%, so every one of the eight parameters is already self-documenting, which sets the baseline at 3. The description's only parameter-level contribution is the cross-reference that the filters mirror search_games, which is helpful but adds no meaning the schema lacks.

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 a given game — and even discloses the ranking mechanism (genres weighted three, tags one). That mechanism plus the 'like a given game' framing cleanly separates it from search_games and get_game.

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?

The phrase 'Takes the same filters as search_games' tells the agent this is the discovery path once a seed game is known and that the filter vocabulary is shared, which is real routing guidance. It stops short of explicit when-not guidance (e.g. use search_games when you have no seed game), so it is clear context without full exclusions.

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