Search Gmail (read-only)

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

Annotations confirm the safe-read profile, and the description adds substantial context beyond them: the truncated return payload (id, subject, from, date, snippet — no body), the $0.10 cost, API-key requirement, and that share tokens are blocked. That is exactly the extra behavioral signal annotations cannot carry.

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-loaded with purpose and scope, then routing, then constraints — each sentence carries information. It runs dense and repeats the read-only framing already in the title, but there is little waste and no 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 search tool with an output schema and full annotation coverage, this is complete: it covers prerequisites, return shape, follow-up tool, hard limits, auth requirements, and cost. An agent needs nothing further to invoke it 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 100%, so the baseline is 3, but the description adds real meaning: it explains the account/email parameter selects among multiple mailboxes and requires list_gmail_accounts, and it gives concrete Gmail operator syntax (from:, subject:, is:unread, newer_than:7d, has:attachment) that shapes how query should be written.

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 (search Gmail inboxes) with explicit scope: one connected inbox, read-only, reusing the Integrations hub Gmail connection. It clearly distinguishes itself from neighbors like read_gmail_message (follow-up), list_gmail_accounts (prerequisite), and the import_*_gmail siblings, which are message-pulling rather than search.

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?

Explicit when/when-not: call list_gmail_accounts first when multiple mailboxes exist, prefer Gmail operators, follow up with read_gmail_message for the body, and it cannot send/archive/delete. It even notes share tokens cannot call it and where to connect Gmail if absent — a full routing story.

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