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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real behavioral context on top: the inclusion thresholds (70%+ positive, 50+ positive reviews), the coverage caveat that adult-only titles are excluded and filtering is best-effort, and the semantic distinction between a `new` release and an `ea_exit`.

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?

Front-loaded with the core definition and alternative-sibling routing, and nearly every clause earns its place. The first sentence is dense with stacked qualifiers and parentheticals, making it slightly harder to parse than necessary.

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 5-optional-param list tool with an output schema and read-only annotations, it covers purpose, filtering semantics, edge cases, and the one sibling overlap. Return contents (price, Deck status, release date, links, `why` lines) are noted, and the output schema carries the rest.

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 only 40%, so the description must compensate and largely does: it explains `upcoming`, `coop` (co-op only), and the meaning of every `ea_exits` enum value beyond the schema's one-liner. It never mentions `n`, leaving the result-count parameter documented only by its default/max in the schema.

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+resource+scope: Steam games released in the last 30 days meeting named rating/review thresholds, plus an `upcoming` mode. It explicitly separates itself from the sibling `trending` ('for what is gaining players now use trending'), so an agent can route without opening any schema.

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?

Gives explicit when-to-use ('what's new / coming out') and the alternative with its condition ('what is gaining players now use trending'). It also prescribes how to describe results via the `ea_exit` distinction ('call those out of Early Access, not new').

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