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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description needs to add only extra behavioral context. It does so by disclosing the default exclusion of browsing noise, the $0.10 cost, and the API key requirement, and by clarifying that 'year' means calendar year. No contradiction with annotations exists.

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 description is four short, information-dense segments, each adding distinct value: what the tool returns, how to specify time, default filtering behavior, and cost/auth constraints. It is front-loaded and contains no filler or redundant wording.

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 four optional parameters and an output schema present, the description adequately covers the main calling patterns, defaults, and constraints. The only notable gap is the lack of an explicit statement about behavior when no time parameters are supplied (e.g., a default range), though this is a minor omission given the output schema.

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 75%, so most parameters are already documented. The description adds value by specifying the preference for explicit from/to over range, listing the allowed shortcut values, and clarifying that 'year' is a calendar year rather than a rolling year. It also restates the default for include_browsing, though the schema already covers that.

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 begins with 'Authenticated user's calendar events,' clearly indicating a read operation on a specific resource, and the tool name 'get_events' supplies the verb. It is not a tautology and is more specific than many sibling get_* tools, but it does not explicitly distinguish itself from related tools such as get_memories or get_trackers.

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?

The description gives clear calling context: prefer explicit from/to dates, use shortcuts such as today|week|month|year|decade, and note that browsing noise is excluded by default. However, it does not state when to use this tool over alternatives, nor does it explain what happens when no time parameters are provided.

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