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

Annotations only say destructiveHint=true with no reversibility detail; the description adds idempotency (previously imported rows are skipped), reversibility (the whole import can be taken back), re-planning against the account state at import time, the untrusted nature of file names, and the confirm gate. This is exactly the extra behavioral context annotations cannot carry.

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 action and packed with useful detail, no filler sentences. It is a single run-on paragraph though, and the oblique line "Names from the file are text written by others" is easy to misread, which costs a point on structure.

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 destructive, 10-parameter write tool with no output schema, it covers side effects, dedupe, undo, size limits, and the preview/execute distinction. What's missing is any statement of required permissions or the shape of the returned plan/summary, so the agent can't fully predict the response.

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 baseline is 3, but the description adds cross-parameter semantics the schema does not: rows are attributed to the user unless the file names a project member's email, and client/project creation is conditional on createClients. It doesn't explain mapping, dateOrder, or durationUnit beyond what the schema already says.

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 and resource ("Imports a CSV of hours") and then enumerates the side effects: creates clients/projects, a task per task name, and one time entry per row. It also distinguishes itself from the sibling preview path by noting the same arguments with a confirm flag flip the behavior from preview to execution.

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?

Explains the when-to-use mechanics clearly: needs confirm: true or you get a preview, and files over 200,000 characters must go through the app's Import page. It never explicitly names preview_time_import as the tool to run first, which is the natural alternative an agent would need.

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