Read Gmail Inbox

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

Annotations already set readOnlyHint=true, confirming read-only behavior. Description adds 'Gmail's DOM changes often — if this returns empty...' which warns of potential instability and suggests workaround. No contradictions.

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?

Four sentences, each serving a distinct purpose: action, return format, fallback strategy, and parameter details. No redundancy, well-structured, and front-loaded with core purpose.

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?

Comprehensive for a simple read tool: describes return format with fields, parameter constraints, and fallback behavior. Output schema hinted by the fields listed. No gaps given the low complexity.

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?

Only parameter 'limit' described with default (20) and max (50). While schema provides default, description adds max constraint and clarifies it's the number of messages. Schema coverage is 0%, so description compensates significantly.

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?

Description clearly states 'Read the Gmail inbox of the active account' with specific verb and resource. It distinguishes from siblings like gv_open_url and google_get_page_content by focusing on reading inbox versus browsing or page interaction.

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?

Explicitly advises when to use alternatives: 'if this returns empty, use gv_open_url to mail.google.com and google_get_page_content (with screenshot) instead.' This provides clear fallback and context for when the tool may not be effective.

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