refresh_cache

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

With no annotations, the description carries the full burden and meets it: it warns that cached data is flushed, clarifies the next call hits the network, and explicitly states auth tokens are NOT cleared. The data-vs-login distinction is exactly the behavioral context an agent needs.

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 short blocks each accomplish a distinct job: what it does, when to use/avoid, and parameter values. 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?

For a single-parameter cache-clearing tool, the definition covers action, trigger conditions, exceptions, and all argument choices. The output format is not critical since invoking the tool successfully does not depend on it.

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 0% and the schema only says target is a string defaulting to 'all'. The description compensates by listing all valid target values ('all', 'steam', 'epic', 'igdb') and restating the default.

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 uses a specific verb ('flush') and names the exact resource ('cached library/metadata data'), stating the consequential behavior that the next call re-fetches. This is clearly distinct from the sibling read/list/auth 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?

It explicitly says when to use the tool (when data may be stale, after installs/purchases) and when not to (for a few specific games, prefer force_refresh on the igdb_* tools). It also rules out auth-token clearing, reducing misinvocation.

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