steam_compare_games

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

Annotations already declare readOnlyHint=true and the description is consistent with that, so the safety profile is covered. The description adds useful behavioral context by previewing what data the tool surfaces (price, reviews, players, Deck, co-op, tags). It doesn't disclose whether the comparison fans out into multiple Steam API calls or how results are rendered, but for a read-only tool this is an acceptable gap.

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?

A single front-loaded sentence: verb, resource, range, dimensions, and use case, with zero filler. Every clause earns its place and the key scoping constraint ('2-5 games') appears immediately.

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 no output schema, the dimension list partially tells the agent what to expect back, and the response_format default hints at markdown rendering. But the description omits the semantics of country_code and response_format and how the comparison output is structured, leaving moderate gaps for what is otherwise a simple tool.

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 low — only appids has an inline description; country_code and response_format have none. The description text mirrors the appids constraint ('2-5 games') and lists comparison dimensions, but never explains country_code's effect on regional pricing or how response_format shapes the output, so it fails to compensate for the coverage gap.

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 ('Compare'), a resource (Steam games), a bounded input range (2-5), and the exact comparison dimensions (price, reviews and trend, players now, Deck, co-op, tags). The 'X or Y?' framing makes it immediately distinguishable from siblings like steam_compare_players and steam_analyze_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 'for "X or Y?" questions' clause gives a clear when-to-use signal, and the 2-5 game range implies a side-by-side selection context. However, it names no alternatives or exclusions — it doesn't tell the agent when to prefer steam_should_i_buy, steam_recommend, or steam_analyze_game instead.

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