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

Annotations declare a non-read-only, non-destructive, non-idempotent operation; the description adds real context beyond them: it does not apply rows (so preview semantics), imports are resumable, all errors block execution, valid=false is a mere draft not a runnable state, and provider record text is untrusted. No contradiction with destructiveHint=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?

Front-loaded with the critical ONLY/NEVER constraint and packed with actionable specifics, but the middle section concatenates several distinct topics (mapping, constants, conversions, lookups, prefixSteps, failure handling) into a dense run of sentences with no structural separation.

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 12-parameter nested-object tool with an output schema present, the description covers the decision-critical surface: input shape, conversion rules, lookup resolution, failure semantics, and the untrusted-data caveat. Return values need not be explained given the output schema.

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 only 17% schema coverage over 12 parameters, the description must compensate and largely does: it defines mapping semantics (actual columns only, targets body.*/pathParameters.*/query.*, deterministic conversions) and explains defaults.body as typed JSON with a worked Name,Days template example. It leaves lookups, headerRow, duplicateMode, and prefixSteps/dependsOn semantics essentially undocumented, so the compensation is strong but incomplete.

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+resource ('Validate/save a resumable import') scoped to an attached CSV/XLSX, and explicitly rules out the adjacent behavior ('NEVER for ordinary record creation'), which distinguishes it from system_prepare_write/system_create_workflow. An agent can identify the tool 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?

Gives explicit when/when-not conditions ('ONLY for an attached CSV/XLSX spreadsheet, NEVER for ordinary record creation') plus operational guidance on where constants go versus mapping. Also tells the agent what to do on failure (inspect validationErrors and repair without changing user intent).

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