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

Goes well beyond the annotations: discloses the confirmation email and calendar invite side effects, that only the attendee (when an email is supplied) gets a reschedule/cancel link while guests do not, that round-robin picks the host by rules unless one is named, and the per-call cost and failure pricing. That is exactly the kind of side-effect and cost context 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-loads the core action in the first clause and packs cost, side effects and the round-robin rule into four tight sentences. The middle sentence about who receives links is dense and takes a second read, but no sentence is filler.

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 12-parameter mutation tool with nested answers and no output schema, the description covers pricing, side effects, notifications and host routing well. The notable gap is the return value — nothing says whether the call yields a booking identifier that calendar_cancel or calendar_move would need, which the missing output schema would otherwise have to supply.

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?

With only 58% schema description coverage, the description usefully explains several undocumented parameters: email gates the self-service reschedule/cancel link, guests are invited by email without that link, host overrides round-robin rules, and confirmation_call_agreed is a consent flag rather than a scheduling option. It still says nothing about timezone, answers, phone, notify or person, so the compensation is partial.

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 ('Book a free time ... for someone') and immediately ties it to the sibling that produces the input ('from calendar_find_times'). An agent can tell this apart from calendar_find_times, calendar_move and calendar_cancel without opening any schema.

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?

Explicitly names the prerequisite source of the slot (calendar_find_times) and gives a conditional rule for confirmation_call_agreed ('only if the person agreed to a call before the meeting'). It does not say when to prefer this over the Google/M365 calendar_create siblings or over calendar_move for changing an existing booking, so the routing guidance is clear but not exhaustive.

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