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

Annotations already declare destructiveHint=true and idempotentHint=false; the description goes beyond them by disclosing that the old token is revoked immediately and that the new token is displayed only once. That is exactly the operational detail that makes an irreversible action safe to invoke, though it omits whether previously issued tokens elsewhere (other connections) are also invalidated.

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, zero waste; the core action and its irreversible consequence are front-loaded ahead of the conditional use case. Nothing needs re-reading.

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 no output schema, the description correctly notes the new token is "shown once," which is the key return-value fact an agent must act on. It could have added that the caller must persist the value immediately, but the essential contract is present for a two-parameter, fully documented 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 100% and both parameters are documented inline, including the conditional note about omitting conversation_token when an account token header is present. The description adds no parameter-level meaning beyond the schema, so the baseline 3 applies.

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 and resource ("Issues a new conversation_token and revokes the old one") plus the immediate-revocation behavior that separates rotation from sibling tools like start_conversation or claim_conversation. An agent knows exactly what this does without opening the schema.

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?

"Use it if the token may have leaked into logs" gives a concrete triggering condition, which is more than most definitions offer. It stops short of stating when NOT to use it (e.g., get_conversation_status for checking validity) or warning that rotation invalidates holders of the old token.

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