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

Annotations cover the safety profile (readOnly, non-destructive, closed-world), and the description adds substantial value beyond that: required mail.read scope, API-key vs non-ChatGPT OAuth requirement, the ChatGPT-profile exclusion, the share-token exclusion, and the $0.05 cost. This is exactly the auth/eligibility context an agent needs before attempting a call.

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?

Front-loads purpose and the returned fields, then usage, then eligibility. Dense but each clause carries information; the parenthetical pricing and 'multi-mailbox after migration' note are slightly cramped but not wasteful.

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?

An output schema exists, so return values need no explanation, and the description fully covers the parts structure cannot: authentication scope, caller eligibility, cost, and how the result feeds sibling tools. Nothing needed to call this correctly is missing.

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 and the schema is a closed empty object, so there is nothing for the description to disambiguate. The mention of returned fields (id, email, is_default) is output-oriented rather than parameter guidance, leaving the baseline score 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 and resource (list connected Gmail mailboxes) and enumerates the returned fields (id, email, is_default), which no sibling tool does. It is immediately distinguishable from search_gmail, read_gmail_*, and the import_*_gmail tools, which it explicitly positions itself before.

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?

Gives clear operational context: use the returned account value on search_gmail / read_gmail_* / import_*_gmail, and connect additional inboxes at /integrations. It states who cannot call it (ChatGPT profiles, share tokens), but does not frame an explicit when-not-to-use beyond eligibility limits.

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