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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety bar is low, but the description adds real behavioral detail beyond them: the 500-row threshold at which the output changes shape, and the fallback of sending the user to a page for the full result. It does not state the output format of the cleaned CSV or any size/performance limits, which keeps it short of a 5.

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?

Three tight sentences: capability and removals first, then the return/size behavior, then the scope limit. No filler, and the most decision-relevant facts are front-loaded.

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?

With no output schema, the description takes on the burden of explaining return behavior and does so precisely, including the conditional response shape. Parameters are fully covered by the schema, so nothing an agent needs to invoke this correctly is missing.

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 description coverage is 100%, so the csv body and the removeRole/removeDisposable defaults are already documented. The description corroborates those two categories but adds no syntax, format, or edge-case meaning beyond the schema, which is the expected baseline when the schema does the work.

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?

Specific verb plus resource ('Clean a lead CSV') followed by an enumeration of exactly what is removed (malformed, duplicate, role-based, disposable) and with per-reason counts. It also draws an explicit boundary against the sibling verify_email with 'Does not verify mailboxes exist', so the agent can separate it from verification, conversion, and combination tools.

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 closing exclusion ('Does not verify mailboxes exist') effectively routes the agent to verification siblings when mailbox existence matters, and the row-count cutoff tells it when a second step (page download) is needed. There is no positive statement of when to prefer this over combine_csvs/convert_csv, so the guidance is clear but not exhaustive.

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