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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description adds the meaningful scope restriction (unread only) and the returned fields, but says nothing about ordering, cap behavior at 30, or whether unread state is affected.

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 sentences, zero filler — the scope is front-loaded and the second sentence only carries the return payload. 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?

For a simple single-parameter read tool with full annotation coverage, this is nearly complete: the description supplies the unread-only scope and the returned fields, which the absent output schema would otherwise leave blank. A note on result ordering would close the remaining gap.

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 single 'limit' parameter already documents default 10 and max 30 in Portuguese. The description adds no format or behavioral detail about the parameter, 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 description uses a specific verb+resource pair ('Lista e-mails não lidos da caixa de entrada Gmail conectada') and further names the returned fields. It is clearly distinguishable from siblings like list_scheduled_messages or get_conversation_messages, though it never explicitly contrasts itself with them.

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 implied by the 'unread' scope and the Gmail inbox constraint, which tells the agent this is the entry point for triaging new mail. There is no explicit when-to-use/when-not guidance and no alternative tool is named for read or all-mail cases.

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