Delete one evaluation dataset item.
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"itemId": "<itemId>"
},
"name": "dataset_item_delete"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| itemId | Yes | Dataset item UUID |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=false, so the safety profile is covered. The description adds nothing beyond that: no mention of irreversibility, whether evaluations or runs referencing the item are affected, whether the deletion is hard or soft, or what confirmation is returned.
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?
A single front-loaded sentence with no filler or redundancy. It is efficient, though its terseness is partly the source of the missing behavioral detail rather than pure economy.
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?
This is an irreversible destructive mutation with no output schema to explain the result, so the description should carry the weight of consequences. It says nothing about permanence, side effects on referencing experiments, or the response shape, leaving an agent under-informed before an unrecoverable call.
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?
Only one parameter (itemId) and schema description coverage is 100%, with the UUID format documented in the schema itself. The description contributes no additional meaning about the identifier, which is acceptable given the schema does the full job — baseline 3.
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?
States a specific verb and resource ("Delete one evaluation dataset item") so the agent knows exactly what is affected. It is distinguishable from siblings like dataset_item_add and dataset_item_update by the verb alone, though it never names them explicitly.
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?
No guidance on when to use this versus dataset_delete or dataset_item_update, and no prerequisites or preconditions are stated. The agent must infer that a dataset item must exist and that this is the removal counterpart to dataset_item_add.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.