Recommend games

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

Annotations already provide readOnlyHint and openWorldHint, but the description goes far beyond them. It discloses the exclusion of owned/wishlisted games, the 0-100 match score and tag attribution, the intentional ordering for variety ('a lower score can sit above a higher one'), and the no-API-key fallback. These are nontrivial behavioral traits that an agent must know to interpret results correctly. No contradictions with annotations are present.

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?

The description is concise yet information-dense, with no filler. It front-loads the purpose, then gives usage examples, defaults, return format, and a fallback behavior in a logical flow. Each sentence carries unique information, and the length is appropriate for the tool's complexity. The structure makes it easy for an agent to parse quickly.

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?

Given the 10-parameter schema (all documented) and no output schema, the description covers the essential missing pieces: what the output contains (candidates, score, tags, caveats), the ordering quirk, exclusion defaults, and the no-API-key fallback. It is complete for an agent to invoke the tool correctly and interpret results, even for a recommendation engine with this many options. No significant contextual gap remains.

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 100%, so each parameter is already described. The description adds value by giving vivid examples for the required `preference` parameter and clarifying that `tags` are exact and can be pinned. It also confirms the default behavior for `include_owned` by mentioning exclusion by default. While it doesn't delve into every parameter, the combination of complete schema and these clarifications is sufficient.

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?

The description opens with 'THE MAIN TOOL' and then states exactly what it does: 'Recommend games matching a stated preference, ranked against what the player actually plays.' It provides concrete examples of preference phrasing, making the tool's purpose unmistakable. It clearly differentiates from siblings by explicitly framing itself as the primary recommendation tool, distinct from search or comparison tools.

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 description gives strong context: it explains the primary use case (matching a stated preference, with examples), notes that owned and wishlisted games are excluded by default, and mentions that it works without a Steam API key as a fallback. However, it does not explicitly state when to use alternatives like search_games or find_similar_games, so it stops short of full exclusion guidance. It provides clear context but no explicit 'when not to use'.

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