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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds a genuine behavioral fact beyond the annotations: the caller needs the contacts.read scope, which is exactly the kind of auth requirement structured fields cannot express.

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?

A single short sentence with the purpose front-loaded and the permission note trailing it — no waste. The word 'additionally' is slightly ambiguous (additional to what baseline permission?), costing a point but not clarity of the core action.

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 zero-parameter exporter with an output schema and full annotations, the description supplies everything needed to call it correctly: what it produces and what scope it requires. It omits only marginal detail like file size limits or whether generation is synchronous.

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 no parameters, so there is nothing for the description to disambiguate; this is the baseline-4 case. No parameter text is expected or missing.

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?

Names a specific verb and resource with the output format: 'Download organization contacts as CSV'. The resource word 'contacts' cleanly separates it from the sibling exporters (export_employees_csv, export_locations_csv, export_policy_pdf) without needing their schemas opened.

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 description states a permission prerequisite ('additionally requires contacts.read') but gives no guidance on when to choose this over alternatives such as list_company_members or get_contact_tab_access, and no exclusions or context for the export.

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