fm_flush_datasets

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

Describes caching behavior and effect of flushing, including return confirmation. Without annotations, it covers main points, though it doesn't detail all side effects.

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?

Concise, well-structured with title, explanation, args, returns. No waste.

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?

Completes the tool picture: explains when to use, what it does, parameter semantics, and return value. Output schema exists so return details are adequate.

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?

Adds meaning to the only parameter 'table': explains default flushes all, and gives example. Compensates for 0% schema coverage.

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?

Clearly states it flushes cached table data from session memory. The verb 'flush' and resource 'cached table data' are specific. It distinguishes from query and load 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?

Explicitly suggests use after data modification or to free memory. Does not state exclusions but context makes them clear.

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