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

Goes well beyond the annotations (readOnlyHint/destructiveHint false), which only confirm it is a safe read. The description enumerates exactly what the preview returns (importable rows and totals, clients/projects/tasks to be created, skipped duplicates, unreadable rows with numbers, plan-limit blocking, settings used, columns), discloses the 200,000-character input limit versus the 8 MB Import page, and warns that file names/cells are untrusted text written by others.

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-loads the core action and its no-write guarantee, then layers return content, limits and the trust warning. It is somewhat run-on and includes several return-value items, but each clause carries information — especially given there is no output schema.

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 9-parameter tool with no output schema, the description covers the critical missing pieces: the shape of the response, the input size ceiling, default-guessing behavior, free-plan blocking, and the prompt-injection caution about CSV-authored text.

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 100%, so the schema already documents all nine parameters including defaults, enums and the mapping field list; the baseline is 3. The description adds only marginal semantics ('guessed from the headers unless given') and repeats the size limit, so it does not meaningfully exceed what the schema provides.

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 (preview a time-import CSV) and immediately distinguishes itself from the write sibling with 'without writing anything: the rows that can be imported.' An agent can tell this apart from import_time_csv without opening either 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?

The dry-run framing ('says what importing it would do, without writing anything') strongly implies when to use it — before committing an import. However, it never explicitly names import_time_csv as the commit counterpart or states when/when-not to preview, leaving that inference to the agent.

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