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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false. The description adds substantial behavioral context: the certificate is issued at payment settlement, emailed as a PDF, and registered against an hash. It also clarifies that no slot, calendar entry, or meeting is created, which is crucial for an agent to understand the tool's side effects.

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?

The description is five sentences, each serving a distinct purpose: the core action, the artifact's nature, the issuance process, the sibling alternative, and the buyer-consent rule. No sentence is filler; it is front-loaded with the most important information and remains compact given the tool's complexity.

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?

Despite having no output schema, the description provides essential outcome details (PDF emitted, hash registry) and operational guidance (payment, buyer choice). It fully differentiates the tool from create_order and covers the required parameters' intent, making the tool actionable for an agent. The lack of an exact response structure is a minor gap, but the description is otherwise complete.

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?

The input schema describes all five parameters with 100% coverage, including detailed explanations for catalogue_token and buyer_confirmed_choice. The description does not introduce new parameter formats or constraints beyond the schema; the buyer-consent guidance in the description largely echoes the schema's instruction for buyer_confirmed_choice. With high schema coverage, a baseline of 3 is appropriate.

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?

The description opens with a specific verb and resource ('Buy a certificate') and explicitly contrasts itself with the sibling tool create_order ('Use this instead of create_order, which is only for booking time'). It also clarifies that certificates are objects, not appointments, eliminating any ambiguity about scope.

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 description explicitly states when to use the tool and names the alternative to avoid: 'Use this instead of create_order, which is only for booking time.' It also adds a buyer-consent guideline ('As with sessions, show the buyer what is on offer and let them choose'), giving clear operational rules beyond simple tool selection.

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