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

Annotations already declare destructiveHint=true, openWorldHint=true, non-idempotent and non-read-only, so the safety profile is partly carried structurally. The description adds real context beyond that: what 'show' returns (table address/name, live access status, update mode, last export, excluded questions) and the three sync modes. It does not call out irreversibility of delete or overwrite semantics of export_all/replace, which a destructive multi-action tool would ideally state.

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?

Purpose and the most important action ('show') are front-loaded before the enumeration of remaining actions. It is a single dense paragraph rather than a scannable list, which is a minor structural weakness, but every sentence carries information and none is padding.

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 9-parameter, 9-action tool with no output schema, the description covers purpose, action inventory, state-reading via 'show', prerequisites, and where logs are found, so an agent can invoke it correctly. What is missing is return/error behavior for the mutating actions and any warning about destructive outcomes, which keeps it below a 5.

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 the schema itself already documents each enum value, cross-field dependencies (sync_mode required for set_sync_mode, schedule_hour/minute for scheduled, export_mode for export_all) and the whole-list semantics of hidden_widget_ids. The prose largely restates the action list, adding little syntax or format detail beyond the schema, so the 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?

The opening states a specific verb+resource (exporting answers to Google Sheets) and then enumerates every action the tool performs, mapping transparently onto the action enum (show, activate, deactivate, delete, save_widgets, save_switchers, set_sync_mode, sync_now, export_all). An agent can tell this apart from the CSV/XLSX/SPSS export siblings because it is the live Sheets-integration manager, not a one-off file export.

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?

It gives clear operational context: 'show' reveals current state, account connection and table selection happen in the cabinet rather than through this tool, and synchronization logs live in get_quiz_integrations. This explicit routing to another tool/cabinet is strong. It stops short of an explicit when-not-to-use rule versus the static export tools, so it is not a full 5.

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