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

Annotations already indicate this is a mutating, idempotent, non-destructive operation, and the description adds useful behavioral context: 'clear' removes an existing answer, the answer applies to a single occurrence, and the operation requires user confirmation. This enriches the annotation-only safety profile without contradicting it.

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 two tight sentences with no filler. The core action and allowed values are front-loaded, followed by the repeating-event nuance and the user-confirmation guardrail. Every sentence carries necessary semantic weight.

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 mutating RSVP tool with strong annotations and a well-described schema, the description covers all essential invocation concerns: status semantics, occurrence-specific behavior, how to target a repeating event, and the confirmation requirement. No output schema is needed because the tool's return value is not central to selecting or calling 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?

Schema coverage is 80%, so the schema carries most parameter documentation. The description adds value beyond the schema by explaining the meaning of the status enum, especially that 'clear' removes the answer, and by defining the default behavior of occurrence_date for repeating events with a pointer to get_plan's event.upcoming.

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 clearly states the action ('Answer whether the person is coming') and the exact allowed values ('yes', 'no', 'clear'), tying directly to the resource 'rsvp'. It also clarifies the special semantics of 'clear' as removing an answer, which distinguishes the tool's purpose from general event editing or availability tools.

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 context for when each status and occurrence_date should be used: repeating events default to the next occurrence, and occurrence_date selects a specific one. It also adds the human-gating requirement 'Only with the user's confirmation.' It does not explicitly name alternative sibling tools or exclusions, but the usage context is unambiguous.

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