get_recently_played_games

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

With annotations already covering readOnlyHint=true, idempotentHint=true, and destructiveHint=false, the description's job is lighter. It adds valuable context beyond the annotations by disclosing the API-key requirement and the privacy prerequisite on the profile. These are genuine additions—none are captured in the structured data. Cannot reach 5 because it omits other behavioral traits like rate limits or timezone semantics, but this is strong for a read-only tool.

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 sentences, each earning its place: the purpose, the return shape, and the access prerequisite. The structure is front-loaded and scannable. It loses a point only because the final two sentences are terse fragments that could potentially be combined, but they are each independently informative and do not waste words.

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 tool with comprehensive annotations, a fully documented two-parameter schema, and an output schema, the description covers the essentials: scope, return content, and prerequisites. Minor gaps exist (e.g., no mention of pagination interplay between count and the two-week window, or timezone handling), but none are blocking for a correctly formed call.

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%—both steam_id (with rich format examples) and count (bounds and default) are thoroughly documented in the input schema. The description adds no semantic meaning about the parameters beyond what the schema already provides. Per the rubric, when schema coverage is high, the baseline is 3, which the description exactly meets.

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 'List games a player has played in the last two weeks' pairs a specific verb with a clear resource, and the return format is stated ('2-week and lifetime playtime'). It implicitly differentiates from siblings like get_owned_games by time-scoping the query. However, unlike the calibration 5 example, it does not explicitly name any sibling alternative to disambiguate selection.

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 useful contextual constraints—'The profile must be public' and 'Requires an API key'—which inform when the tool can be used. However, it offers no explicit when-to-use comparison against siblings (e.g., when to prefer this over get_owned_games), nor does it list exclusions. It satisfies the 'clear context' bar but stops short of explicit alternatives, so a 3 is appropriate.

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