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

Annotations only declare destructiveHint=true, so the description earns credit for disclosing that inventory is held while the session is open, that nothing is committed until checkfront_create_booking, and that a session_id is returned for reuse. It does not explain what makes the operation destructive (e.g. 'remove' clearing a line) or any session expiry/error behavior, so it stops short of a 5.

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?

Front-loaded with the core action, then branches into the three modes; the endpoint reference is a useful trailer. It is dense and slightly over-packed in the first sentence, but virtually every clause carries 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 4-parameter, nested-object, no-output-schema mutation tool, the description covers workflow position, input provenance, and the returned session_id. It omits failure modes and session lifetime/expiry, which would be needed for a 5.

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% (baseline 3), and the description adds relational meaning the schema can't express: line_id is only meaningful 'with a single slip' to REPLACE a line, and alter changes are keyed by line_id with a number setting quantity and 'remove'/'optin'/'optout' for package add-ons.

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 ('Start or modify a booking session') and enumerates the three supported operations (add SLIPs, replace a line, alter lines). It also distinguishes itself from the sibling checkfront_create_booking by stating 'NOTHING is booked until checkfront_create_booking'.

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?

Explicitly states the prerequisite for input ('SLIPs from a rated checkfront_get_item / checkfront_list_items call'), the condition for omitting session_id ('Omit to start a new session'), and the lifecycle boundary relative to create_booking. An agent knows exactly when to call this versus create_booking.

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