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

Goes well beyond annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) by disclosing atomic failure semantics ('valid=false, csv_text=null, never a partially transformed file'), row preservation, output ordering, and operation cost. The only thin spot is the shape of the 'findings' payload on failure, but the failure contract itself is unusually clear.

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?

Front-loaded with the core capability, then layered with failure contract and exclusions in compact declarative sentences with no filler. Slightly dense and clause-heavy in the middle, but every sentence carries distinct 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?

No output schema exists, so the description must describe returns, and it does: csv_text plus valid plus findings, with the null-on-failure rule stated. Given the rich nested recipe schema, this is close to sufficient, with only the findings structure left unspecified.

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?

With schema_description_coverage at 0%, the description must carry the parameter burden; it clarifies that rules reference original input headers, that version-1 recipes are caller-owned, and that output follows recipe column order. It says nothing about the table input shape (rows vs csv_text vs delimiter), spreadsheet_safe, or request_id, so the compensation is partial.

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?

Opens with a specific compound verb set (select, rename, derive, convert) applied to columns via a version-1 recipe, which precisely describes the transformation resource. It also names the sibling it is not (reconcile_tables for two-file matching), letting an agent distinguish it without opening the schema.

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?

Explicit scope boundaries are given as exclusions: 'No arithmetic, arbitrary code, schema inference or destination writes,' plus a named alternative for a different task shape. The agent knows both when to reach for this tool and when to route elsewhere.

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