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

Annotations only indicate the tool is a non-read operation. The description adds valuable behavioral context: default is_internal=true, public comments appear on the customer's ticket page, and app_url is an internal deep link that must not be shared with customers. This goes beyond what annotations alone communicate.

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 concise yet information-dense. Each sentence adds a distinct value: the action, the default internal nature, how to make a public reply, and caution about app_url. There is no redundancy or filler; structure front-loads the main purpose and then gives operational details.

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 create operation with one nested parameter object, the description covers the primary behavior, defaults, customer visibility implications, and link usage warnings. It also cross-references another tool for obtaining a public URL. No output schema is present, but for a write operation this level of detail is sufficient and 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 schema shows nested fields (text, is_internal, submission_id) but has minimal descriptions; the description compensates by explaining the semantics of is_internal (default true, how to switch to public). It indirectly clarifies submission_id's role as the ticket identifier, but does not explicitly describe the 'text' field or its optionality, leaving a small gap.

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 clear action verb and resource: 'Add a comment to a ticket.' It immediately distinguishes between internal and public comments, making the tool's purpose distinct from sibling read/list or destroy tools.

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?

It explicitly states the default behavior (internal note) and provides the exact condition for using is_internal=false to make a comment visible to customers. It also warns against sharing app_url internally and directs users to public_url from retrieve_ticketsubmissions for customer-facing links, giving both when-to-use and alternative guidance.

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