create_csv_table

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 the internal steps: reads header, samples rows, infers types (Int64/Double/String), builds Csv.Document M, declares every column, and refreshes. It also explains pathExpression behavior and the default of embedding the absolute path, giving a clear mental model.

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 sentences, front-loaded with the main action. The first sentence packs the core workflow and benefits; the second addresses the key parameter nuance. No redundant or filler content, every clause earns its place.

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 create/mutation tool with no annotations and no output schema, the description is remarkably complete. It explains the full process, parameter control, and associated workflow. It doesn't need to describe return values (none specified) and sufficiently covers error-sensitivity by noting the CSV must be staged. The relationship to siblings rounds out the context.

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 coverage is 80% (4/5 params documented), with sessionId lacking description. The description adds valuable semantics beyond schema: clarifies csvPath as a 'staged' CSV, explains sampleRows role in inference, and provides a concrete pathExpression example with default behavior. This goes beyond the baseline and compensates for the missing sessionId context.

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 the tool's purpose: 'Create a fully-typed import table from a (staged) CSV in ONE call' with a specific verb and resource. It distinguishes from siblings by mentioning 'Removes the add_data_column-per-column grind' and explicitly pairs with stage_excel_to_csv / unpivot_weekly_csv, making it unambiguous.

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?

It provides explicit when-to-use context: when you need to import a staged CSV with type inference in one call, and contrasts with the alternative add_data_column approach. It also names companion tools (stage_excel_to_csv / unpivot_weekly_csv), guiding the agent on workflow integration.

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