research_export

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

Goes beyond the annotations meaningfully: 'confined local' signals a sandboxed write target, 'formula-safe CSV' discloses CSV-injection sanitization, and the no-remote-fetch line corroborates openWorldHint=false. It does not say what happens if a file of the same name already exists, which matters given idempotentHint=false.

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?

Two short sentences, no filler, and the key scoping caveat is front-loaded in the very first clause. Every phrase carries information.

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 3-parameter export tool with no output schema, the description covers domain, formats, and the sandbox/security posture. The remaining gap is the return value (path of the written file or a confirmation), which an agent must inspect the result to learn.

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 description coverage is 0%, so the description must compensate. It maps indirectly to the parameters (rows = caller-supplied rows, format = JSON/CSV, with CSV described as formula-safe), but 'name' is never explained — whether it is a filename, a label, or a confined path segment is left ambiguous.

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 (export) plus the resource (caller-supplied structured research rows) and the two output formats (JSON / formula-safe CSV). 'Never fetches a remote dataset' helps separate it from data_export_ohlcv and strategy_export, though those siblings are not named directly.

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 negative clause ('never fetches a remote dataset') implies this is for data the caller already holds, which is useful routing context. However, it never says when to pick this over the many sibling export tools (strategy_export, data_export_ohlcv, watchlist_export, drawing_export) or what preconditions exist.

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