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

Annotations already establish readOnly=false, idempotent=true, destructive=false, openWorld=true. The description adds genuinely non-redundant behavior: vouchers already used in bookings cannot be modified and return 404, and the update is a full replace requiring every required field to be resent. That is exactly the kind of state/permission context annotations don'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 an Overview, then scannable sections for when-to-use, return values, and caveats. Sections are short and each carries content; the Quick Start paragraph lightly restates earlier material but does not bloat the definition.

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 12-parameter mutation with no output schema, the description covers what it needs to: it explains the return (success confirmation plus the updated voucher), the full-replace semantics, and the 404 constraint on used vouchers. The only omission is routing between this tool and the status-specific sibling.

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 100%, so the schema documents all 12 parameters and the baseline is 3. The description adds a nuance the schema cannot express: this is a full-replace update where all required fields must be provided, not just the ones being changed, which prevents a partial-update mistake.

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 (modify) and resource (an existing voucher's settings) and enumerates the modifiable surfaces: discount values, validity periods, usage limits, status. An agent can tell it apart from read siblings like get_vouchers_voucherid, but it does not distinguish itself from the dedicated put_vouchers_id_status sibling even though it claims status changes as a use 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?

The 'When to Use' bullets give real context (extend validity, adjust discounts, update limits, status changes), which is better than nothing. However, no when-not conditions are stated and no alternatives are named, and the status-change bullet collides with the put_vouchers_id_status sibling without explaining when to prefer one over the other.

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