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

Annotations already flag destructiveHint=true and idempotentHint=true; the description earns credit beyond them by stating partial-update semantics ("Only the fields you pass change"), the null/empty-string deletion convention, and the not_invited side effect that revokes a moment from an invitation. It does not mention whether clearing is reversible or what permissions are needed, which is the main remaining gap for a destructive tool.

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?

Three tight sentences with the core action, the update semantics, and the exception front-loaded in that order. The em-dash aside about the RSVP source could be folded in, but nothing is redundant.

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 16-parameter destructive mutation with no output schema, the definition covers the non-obvious behaviors: partial update, deletion sentinel, and moment revocation. It leaves out reversibility, permission requirements, and the side effect of category auto-creation, which are described only in the 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?

With 16 parameters at 63% schema coverage, the description adds the single most important rule an agent needs — omitted fields are untouched, null/empty string clears — which the schema does not state. It also adds meaning to the nested answers structure via the not_invited status behavior, though individual fields like size, category, and children get no elaboration beyond the schema.

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?

"Changes an invitation: its details, and the answers per moment" gives a specific verb plus resource and covers both halves of the mutation (scalar fields and per-moment answers). The qualifier "for an RSVP the couple got by phone or in person" frames the scenario well, though it never names the sibling it differs from (add-guest, delete-guest) so an agent must infer the boundary.

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 phone/in-person RSVP framing implies when this tool applies rather than a guest self-service flow, and the clearing rule tells the agent how to use it. There is no explicit when-not guidance and no reference to the obvious siblings, so the routing decision is only implied.

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