set_filter

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses destructive effects (hiding rows), evaluation over cached and literal values, formula-related warning behavior, refusal for hazardous workbooks unless allow_loss is true, auto-backup, atomic verified save, and refusal while the file is open in Excel.

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 dense and front-loaded, with no filler, but the single-sentence structure with many semicolon-separated caveats is harder to parse than a short structured list would be. It earns its words but could benefit from clearer segmentation.

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 complex mutating tool with no annotations, this is notably complete: it covers safety, backup, save behavior, and row-hiding semantics. Gaps remain in defining what makes a workbook 'hazardous' and what verify_com controls, but the agent has enough to invoke the core operation 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 narrative must compensate. It meaningfully explains criteria structure, ops semantics, AND combination, allow_loss, backup behavior, and the location-as-range concept. However, verify_com is left unexplained, and path and sheet receive only implicit meaning from their names.

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: applying an autofilter over a range with a header row and hiding non-matching rows. It also distinguishes this from simply storing filter criteria in .xlsx, which clarifies its unique role among siblings like query_range and clear_filter.

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 provides clear operational context: criteria are evaluated and rows are physically hidden, with behavior for uncalculated formulas and hazardous workbooks. It does not explicitly name alternative tools such as clear_filter or query_range for when to use them instead, but the semantics are clear enough to guide selection.

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