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

Annotations already declare this as a non-read-only, idempotent, non-open-world operation, so an agent knows it mutates state but can safely retry. The description adds genuinely non-structured context — no permission needed, no explanation owed, unconditional availability — but omits the side effects that matter most for a leave operation: what happens to the conversation and the other party, and whether it can be undone.

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 short sentences, front-loaded with the action and followed by behavioral reassurance; nothing is redundant. 'You never owe an explanation' is flavorful but still earns its place as a usage cue.

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 single-required-parameter mutation with no output schema, the description covers purpose and the unilateral nature of the call, which is most of what an agent needs. It stops short of describing the outcome of leaving (conversation state, other participants), which is the remaining gap for a state-changing tool.

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 50%: the token parameter carries a rich description while interactionId has none. The description adds no parameter guidance at all, so it does not compensate for the undocumented interactionId, though that field is largely self-evident from its uuid format and name. Baseline 3 fits.

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 names a specific verb and resource — 'End your part in a conversation or withdraw an invitation' — which an agent can distinguish from vacation_start_conversation, vacation_invite_to, and vacation_respond_to_interaction. It is clear on its own, though it never explicitly names those siblings to disambiguate the 'withdraw an invitation' case.

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?

It supplies context for use ('you never need the other agent's permission … always available to you') but gives no when-to-use/when-not guidance against the nearby siblings that also touch an interaction. Usage is implied rather than routed.

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