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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the interesting behavior itself: data is redacted per row (handles and profile links only for unlocked creators, emails only for already-revealed ones), rows are rank-ordered, and the call costs nothing. The notable omission is any sense of output size, row caps, or truncation behavior for a potentially large CSV.

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?

Two dense, front-loaded sentences with no filler; the output format and redaction rules come first. The final clause ('Save csv to a file named filename') is terse to the point of being ambiguous about where the filename comes from.

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 correctly steps in to describe the return value as CSV text with one row per creator and which columns are populated. For a two-parameter read tool it is nearly complete, missing only volume/truncation expectations and empty-result behavior.

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%, including an enum and a description for searchId, so the schema already defines both parameters. The description adds no meaning to searchId or to the 'all' vs 'added' scope choice, and its trailing 'filename' reference points at something that is not actually a parameter, which could momentarily confuse an agent about what to pass.

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 ('Returns a search's results as CSV text') plus the shape of the output ('one row per creator in rank order'), which distinguishes it from get_search and search_creators in the sibling list. An agent can tell this is the export path, not the browsing path, without opening a 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 clear context for use: it is the dashboard-equivalent export, it is 'Free' (contrasting with credit-consuming siblings like reveal_contact/unlock_creator), and it ends with a directive to save the CSV to a file. It stops short of naming an explicit alternative or a when-not condition (e.g., use search_creators for paging/inspection instead of a bulk dump).

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