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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: it exports only active accounts, enumerates the exact columns produced, and notes it mirrors the web download and REST data/export_accounts endpoint.

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 core action, then the column list and return contract. The column enumeration is slightly long but earns its place by telling the agent exactly what the CSV contains; no filler prose.

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?

No output schema exists, but the description supplies the return shape ({csv_data, row_count}) and clarifies the header row, so an agent knows what it will get back. Complete for a zero-parameter export tool.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The column list is output semantics rather than input semantics, but it is still useful.

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 (export) + resource (active accounts) + format (CSV text), and it explicitly distinguishes itself from the transactions CSV export sibling. An agent can tell this apart from export_transactions_csv and export_all_data 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?

States the scope ('active accounts only') and points to the transactions CSV export as the separate path for transactions, which routes the agent away from a plausible mistake. It stops short of naming export_all_data as the alternative for a full dump, so it is clear context without full exclusion coverage.

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