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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuine context beyond them: result ordering (oldest first), what the thread contains (request note, accept/decline note), and an auth fork between guest_email and an agent token.

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 sentences, front-loaded with the resource and its ordering, then usage, then parameter guidance. The parenthetical is slightly long but each clause carries information; nothing is redundant with the schema or annotations.

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?

No output schema exists, and the description compensates by describing what the thread returns and in what order. With only two params and read-only annotations, the remaining gap is minor detail like pagination or thread length limits.

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 description coverage is 0%, so the description must carry the load, and it does for guest_email ('the email the booking was made with') plus the agent-token carve-out. booking_id is left unexplained as the obvious identifier, a minor gap but not a blocking one.

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: reads the guest-host conversation about a booking. It also names the scope and ordering ('oldest first, including the guest's note and the host's note'), which distinguishes it from siblings like send_message or ask_host that write to the same thread.

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?

Gives a concrete use case ('Use it to relay the host's replies') and a conditional rule for the credential param ('Pass guest_email ... unless you connect with an agent token'). It does not explicitly name alternative tools, so it stops short of the when-not/alternatives bar.

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