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

With no annotations, the description carries the burden of disclosing side effects. It mentions that payment history is updated and that the subscription may revert, which are important behavioral outcomes. It also states that it only works on unpaid invoices, implying failure on paid ones. It could add details on error handling or irreversibility, but the key behaviors are covered.

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 and front-loaded. The first sentence captures the action, followed by relevant constraints and consequences. The @param and @return sections are clearly formatted. No superfluous information is included.

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?

The description covers the purpose, parameter, return format, and side effects. The output schema exists, so return values are partially handled. It could be more complete by specifying error scenarios (e.g., what if invoice is paid or not found) and whether deletion is permanent, but for a simple delete operation it is fairly 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 has no descriptions for the single parameter (invoice_id), and schema coverage is 0%. The description compensates by stating '@param invoice_id: The database invoice_id', clarifying that the ID is the database identifier, not an external reference. This adds meaningful context beyond the schema's type definition.

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 clearly states the action: 'Deletes an unpaid invoice, updates payment history.' It identifies the specific resource (unpaid invoice) and scope ('Only works on unpaid invoices'). This distinguishes it from any sibling tools, none of which perform deletion.

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 provides clear context on when to use the tool: only for unpaid invoices. It also explains the consequence ('subscription will likely revert to its last state'). However, it doesn't explicitly mention alternatives or when not to use beyond the unpaid invoice restriction, but the constraint is clearly stated.

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