lbb_evals_delete

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

It goes well beyond the annotations by explaining that items are deleted, subsequent gets/exports return 404, the next workflow save creates a new dataset, and the server reads the dataset first to name it and its item count. It also details the approval flow, decline and blocked-client outcomes, and the LBB_MCP_DESTRUCTIVE=allow override.

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 front-loaded with the action and consequence, then proceeds through approval behavior. Each sentence adds operational information for a destructive tool, and none are wasted.

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 operation with no output schema, the description covers data loss scope, downstream effects, approval requirements, decline outcomes, and environment override behavior. An agent has enough context to call it correctly and understand the risks.

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 100%, so the input schema already documents id, graph, and detail. The description confirms deletion is by id but adds no meaning about graph targeting or detail-level behavior beyond the schema.

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: 'Delete an Evals dataset by id, with its items.' This clearly distinguishes it from the read-oriented sibling lbb_evals and tells the agent exactly what entity is removed.

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 implies usage by explaining post-deletion effects and what happens on later gets/exports, but it never explicitly states when to use this versus alternatives or when not to use it. The routing context is adequate but incomplete.

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