refresh_sources

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly states it is a read-only operation that does not modify files, which is valuable context for a cache-clearing tool. It does not mention global scope or performance effects, but those are minor for a parameterless refresh operation.

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?

The description is two short, purposeful clauses: it front-loads the main action, then states the effect and the read-only safety guarantee. Every sentence earns its place with no redundancy or 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 parameterless cache-refresh tool with an output schema present, this description provides enough context: what the tool does, how it affects future queries, and that it does not modify files. An agent can select and invoke it correctly without further detail.

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?

The tool has zero parameters and the input schema is an empty object, so there are no parameter semantics to clarify. The baseline of 4 applies because no additional parameter explanation is needed.

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 opens with a specific verb and resource: '清除数据源缓存' (clear data source cache), and explains the practical effect: the next query re-reads CSV/SQLite. This clearly distinguishes it from sibling query/analysis tools like sql_query, preview_data, and list_sources.

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 use case is implied—refresh presumably when cached data is stale so subsequent queries re-read the source—but the description does not explicitly state when to use this tool versus alternatives, nor does it give exclusions. It makes the intent understandable but leaves the decision somewhat to inference.

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