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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the destructive nature is covered. The description adds the conditional secondary behavior of 'remove platform-seeded bytes when safe,' which is extra context beyond the annotations. It does not explain what 'safe' means, but the annotations mitigate the need for a full disclosure.

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 a single, efficient sentence that front-loads the primary action ('Delete an owned TON Storage bag reference') and appends the conditional behavior ('and remove platform-seeded bytes when safe'). Every word earns its place with no redundancy.

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 destructive tool with two required parameters and no output schema, the description provides the core purpose but omits the confirmation semantics of confirmBagId and the definition of 'safe.' This leaves meaningful gaps for correct invocation, making the description minimally viable but not fully 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?

Schema description coverage is 0%, and the description does not mention bagId or confirmBagId at all. The parameter names imply their roles (an ID and a confirmation), but the description provides no explicit meaning, especially the critical requirement that confirmBagId matches bagId. The description fails to compensate for the schema's lack of descriptions.

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 uses the specific verb 'Delete' and identifies the resource as an 'owned TON Storage bag reference,' adding a secondary conditional action of removing 'platform-seeded bytes when safe.' This clearly distinguishes it from sibling tools like create_bag, pin_bag, and list_bags, which have different purposes.

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 phrase 'owned' and 'when safe' imply conditions for use, suggesting the tool is only for bags the user owns and only under certain safety conditions. However, there is no explicit guidance on when to use this tool vs. alternatives, nor are any sibling tools named or excluded, so usage context is only implied.

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