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

Annotations already declare readOnlyHint, non-destructive, and closed-world, so the safety profile is covered. The description adds genuine behavioral context by stressing the metadata-only, cell-free nature of the read, which implies a small response and no data exposure. It doesn't discuss auth or limits, but the mailbox schema parameter covers auth.

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 scope-defining constraint ('without reading any cells') front-loaded before the workflow guidance. Every clause earns its place.

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 usefully enumerates the return contents (tabs, sizes, named ranges), which is the key missing piece an agent needs. Auth is handled by the mailbox parameter description. Minor gaps remain around response limits or behavior on invalid IDs, but the definition is sufficient to call correctly.

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 50%: mailbox is fully documented in the schema (including the list_authorized_mailboxes pointer), while spreadsheetId carries no schema description. The description adds nothing about either parameter, and spreadsheetId's format is only inferable from the tool name. Baseline 3 is appropriate.

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+resource (read a spreadsheet's structure) and pinpoints the returned payload: tabs, their sizes, named ranges. The phrase 'without reading any cells' cleanly distinguishes it from the sibling read_google_sheet_range, so an agent can pick it apart without opening either 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?

'Call this first to learn what tabs exist, then read a range from the one you want' gives explicit sequencing with the alternative tool. It states both when to use it (before reading data) and what the next step is, leaving nothing to inference.

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