Player reviews

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

With no annotations, the description carries the burden and it discloses a non-obvious limitation: old dates are not accessible and fail with a clear message. It does not describe return shape or ordering, but for a read-only reviews tool the key behavioral caveat is covered.

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 with the main purpose first, followed by the critical limitation and the alternative. Every sentence adds information 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?

The description, combined with a schema that documents most parameters, gives an agent enough to call the tool correctly: required appid, optional filters, and the historical limitation. A return-format note would be a nice addition, but the tool name and title make the output self-evident.

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 67%, and the description adds conceptual meaning by grouping filters into 'date window', 'sentiment', and 'players with real time', mapping to since/until, voted_up, and min_playtime_hours. It does not discuss limit, but the schema and tool context make it self-explanatory.

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 states the resource ('Reviews for a game') and the three optional filter dimensions (date window, sentiment, player time) with a clear verb implied by the tool name. It also names get_review_timeline as a different tool, so it is easy to distinguish from siblings.

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?

It explicitly says only recent windows can be read and gives a direct routing rule: use get_review_timeline for old history. This tells the agent when to call this tool and when not to.

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