recalculate

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

With no annotations provided, the description fully discloses key behaviors: it mutates the workbook (recalculates), can permanently delete external links irreversibly, can fail silently if LibreOffice exits without writing, and requires LibreOffice to be installed. It also warns about the false positive of 'recalculation passed' not meaning 'result correct'. This is comprehensive behavioral disclosure that goes beyond what annotations would normally cover.

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 long but every sentence serves a purpose. It front-loads the core purpose and then logically groups safety, parameters, and returns. While concise would ideally be shorter, the density of critical information justifies the length. No fluff.

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?

Given the complexity of this tool (recalculation with external link risks, silent failures), the description is complete. It covers prerequisites (LibreOffice), side effects (permanent deletion), and error handling. With no output schema, it also describes return values in sufficient detail. An agent has everything needed to decide and invoke correctly.

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 schema has 0% description coverage, so the description fully compensates by explaining every parameter: timeout for large workbooks, force for overriding external link risks, and file_path implied as the target. It also describes the return format (total_errors, errors_by_type) even though there is no output schema, which is extra value.

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 clearly states that the tool recalculates formulas and scans for errors, and it explicitly distinguishes itself from sibling tools by positioning it as a pre-delivery validation step. The phrase '重算公式并扫描错误' is a specific verb+resource, and the description differentiates it from tools like scan_formula_errors and read_range, which is genuinely useful.

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 description gives explicit context for when to use it: after writing formulas with openpyxl, because read_range would return None otherwise. It also explains when not to use it in risky situations (external links) and provides details about the force parameter as a conditional alternative. This is unusually thorough guidance.

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