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

Annotations already declare readOnlyHint/idempotentHint true and destructiveHint false, but the description adds genuinely new behavioral context: the link is single-use with a one-hour expiry, Google emails the attendee an invitation, and read/draft-only API keys receive "[redacted]" instead of a usable link. The only gap is the mild tension between idempotentHint=true and a link that works exactly once, which is left unexplained.

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?

The core behavior — what the link is, who it targets, that it is single-use for an hour — is front-loaded in the first sentences. The remaining sentences about Outlook, redaction, and pricing are dense but each adds actionable information, though the overall flow reads as run-on prose rather than clearly separated concerns.

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 still tells the agent what comes back (a link, or "[redacted]"), how long it lives, what happens downstream (busy-time avoidance, calendar entries, attendee invitations), and what to do next. Only the permission model's exact boundaries and the idempotency question are left fuzzy.

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 only 50%, so the description has to carry weight — and it does: it explains that `person` (email) switches the target from the business calendar to that individual's own. The undescribed `provider` enum is implicitly constrained to Google by the surrounding text, which notes Outlook goes through microsoft365 instead.

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?

The description states a specific verb and resource — it produces a one-time link that connects a Google calendar — and clarifies that the link targets either the business's calendar or, with `person`, that person's own. It distinguishes itself from the Outlook path by pointing at the microsoft365 tools, though it never mentions the nearby `google_connect` sibling, leaving some ambiguity about which one actually performs the connection.

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?

It names the alternative for Outlook calendars (the microsoft365 tools) and states the follow-up step: after connecting, select the calendar via `calendar_setup connected_calendar_id`. What is missing is an explicit when-not-to-use note relative to `google_connect`, which sits right next to it in the tool list.

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