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

Annotations already declare a safe, idempotent read. The description adds real behavioral context beyond that: sendEnabled defaults to false, it gates send_draft for IMAP/iCloud/Google/Microsoft, and it is explicitly NOT the operator-only emergency-send flag — a useful disambiguation agents would otherwise get wrong.

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 the returned data, then adds two short conditional notes. Every sentence carries information, though the plan/inbox-limit phrasing is slightly dense and could be tightened.

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 does the job of naming the returned fields and their meaning, including the default value of sendEnabled. It omits what happens when unauthenticated or on an unsupported provider, but an agent has enough to call 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?

Zero parameters, so the baseline is 4. The description instead spends its budget documenting return semantics (the slot triple, sendEnabled), which is appropriate given there is no output schema.

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 ('Returns the account's plan, status...') and enumerates the exact returned concepts: slots (paid, inUse, free), inbox limit, sync window, send availability. Clearly distinct from list_inboxes or get_send_diagnostics.

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?

Implies when to consult it: 'Adding an inbox needs room on the plan' points to pre-checking before add_inbox, and the sendEnabled explanation points to checking before send_draft. It never explicitly says 'use this instead of X', so it falls short of a 5.

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