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

Annotations only declare readOnly=false, destructive=false, openWorld=true. The description adds substantial context beyond that: the reservation is 'pending until Mariana Tek confirms it,' confirmation happens per-call by default and can be toggled off, it 'reaches other people' so the user must confirm each call, and it needs a Cotlet API key with app access. This is exactly the behavioral disclosure annotations can't carry.

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 and well ordered (purpose, payment, spot, pending state, confirmation, auth). Slight redundancy between the first two sentences, which restate the same one-customer/one-class/one-payment idea, keeps it from a 5.

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 mutation tool with no output schema, the description covers everything an agent needs: pending-vs-confirmed lifecycle, per-call confirmation behavior, user-consent requirement for an outward-facing action, and auth requirements. The safety profile is covered by annotations and not contradicted.

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%, so all four parameters are already documented. The description reinforces the payment_option_id default and spot behavior, and adds the 'Pick-A-Spot' nuance, but adds little beyond what the schema says. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Specific verb+resource: 'Reserve a spot for a customer in a class, paid with one of the customer's memberships or credits.' It states the exact scope (one customer, one class, one payment source), which cleanly distinguishes it from siblings like add_to_waitlist, cancel_reservation, and check_in_customer.

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 actionable conditional guidance: 'Leave payment_option_id out to use the first valid option' and 'For Pick-A-Spot classes pass spot, otherwise any open spot is used.' Clear context for use, but it never explicitly names an alternative sibling (e.g., waitlist vs booking) or a when-not-to-use condition.

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