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

Annotations already flag destructiveHint=true and non-idempotent, and the description goes well beyond them: removal is into the member's Trash (soft delete, recoverable), only self-added events can be removed, events inserted by another source are removed at that source, and public hosted events are out of scope. That is material behavioral context an agent cannot infer from annotations.

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 the trigger condition and the single-event scope, then the safety protocol, then exclusions — a sensible ordering. The prose is dense and nearly every clause carries information, though one clause ('one another source put on the calendar') is garbled and slightly slows parsing.

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 destructive, no-output-schema mutation, the description covers what is removed, where it goes (Trash), which events are eligible, and the confirmation protocol. It stops short of saying what the call returns or how to undo the deletion beyond the Trash reference, which is a minor remaining gap.

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 schema already documents id, person, dry_run and project, including the 'do this first' note on dry_run. The description reinforces the dry_run-first sequence and the id provenance but adds no new format or edge-case detail for person/project. Baseline 3 is appropriate.

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 set (cancel/delete/remove) against a specific resource (one event on the member's own Connections calendar), and explicitly scopes to a single event by id into the member's Trash. It also carves out what it is not: not a reschedule (connections_calendar_update) and not a public hosted event cancellation.

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 concrete trigger utterances ('cancel my 3pm', 'take lunch with Sam off my calendar'), names the prerequisite source for the id (connections_calendar_list), and routes the time-change case to connections_calendar_update. It also mandates a dry_run-first confirmation workflow, which is exactly the operational guidance an agent needs.

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