Export all clients for the active company as a CSV file, optionally overriding the company with a UUID. Use it to generate base64-encoded CSV data for download or processing.
Export all clients for the active company as a CSV file. Returns base64-encoded binary data representing the CSV file contents.
| Name | Required | Description | Default |
|---|---|---|---|
| companyId | No | Company UUID override (uses active company if not set) |
Changes observed during successful MCP inspections.
v1.0.17Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds genuinely non-derivable behavior: the result is base64-encoded binary rather than a normal JSON payload, which materially changes how an agent must handle the response. It stops short of mentioning payload size or whether output is ever truncated.
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 tight sentences, zero filler, with the resource scope front-loaded and the return encoding stated immediately after. Nothing could be removed without losing information.
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 covers the one thing an agent could not otherwise know: the response is base64 binary. For a single optional parameter, read-only export this is close to sufficient; only size/limits and the XML alternative are unaddressed.
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% and companyId already documents the active-company fallback, so the schema does the heavy lifting. The description's phrase 'for the active company' reinforces the default but adds no format or constraint detail beyond the schema; baseline 3 applies.
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 ('Export all clients ... as a CSV file') with a clear scope ('for the active company'). It implicitly separates itself from clients_list, but never names the close sibling clients_export_saga_xml, which serves the same data in XML, so the agent must infer the format split from the name alone.
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?
Usage is only implied: the word 'Export' and 'CSV file' suggest bulk-download use, and the schema note about active-company override hints at scope. There is no explicit when-to-use, no when-not, and no pointer to the sibling XML export or clients_list for paginated reads.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.