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

Adds substantial context beyond annotations: two return fields (authorizationUrl, state), the hand-off to the user's browser, and a 10-minute link expiry. It does not explain why destructiveHint is true (e.g. whether re-connecting replaces/revokes an existing mailbox connection), which is the one remaining behavioral gap.

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?

Three tight sentences, front-loaded with the action, then the return contract, then the follow-up loop and expiry. No filler; every clause carries information the caller needs.

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 covers the return payload, the required user interaction, the polling procedure, and the expiry window. For a 1-param initiation tool this is complete.

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 0% for the single 'provider' param, but the description compensates by spelling out that the two enum values correspond to Google Workspace and Microsoft 365 mailboxes. That gives the enum contextual meaning beyond the bare values.

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 ('Start connecting') plus resource ('Google Workspace or Microsoft 365 mailbox by OAuth') and explicitly distinguishes itself from the sibling it hands off to (check_oauth_connect). The '(no password)' note sharpens what kind of connection this is.

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 explicit sequencing: call this, hand authorizationUrl to the user, then poll check_oauth_connect with the returned state every few seconds until 'connected' or 'failed'. Names the follow-up tool and the terminal states, 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.