delete_eval_pack

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

With no annotations, the description carries the full burden. It discloses a key condition ('only if no job requires it') but omits critical behavioral details such as whether deletion is permanent, what error occurs if a job requires the pack, or any consequences for dependent resources. The description is too sparse for a destructive operation.

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') and packs the essential qualification ('one of your own eval packs') with a condition. 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 no output schema and no annotations, the description should cover return values, error handling, and prerequisites. It only gives a brief condition. Sibling tools like list_eval_packs provide surrounding context, but the description itself is incomplete for safe invocation.

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 provides a required 'packId' string with no description, and schema description coverage is 0%. The description does not elaborate on what packId represents or how to obtain it, only indirectly referencing 'your own eval packs.' This leaves the parameter under-specified and does not compensate for the lack of schema documentation.

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 specifies the action (delete), the resource (eval packs), and the scope (one of your own), distinguishing it from sibling tools like publish_eval_pack or set_eval_pack_active. The additional condition 'only if no job requires it' further clarifies the tool's unique role.

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 gives a clear context for when to use the tool: to delete an eval pack that you own and that is not required by any job. It does not explicitly name alternatives, but the condition provides practical guidance. A minor improvement would be to suggest using list_eval_packs or my_eval_packs to find pack IDs.

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