ml_experiment_create

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

Annotations already establish readOnlyHint=false and destructiveHint=false, so the write-but-not-destructive profile is covered. The description adds the '(long-running)' behavioral flag, which is genuinely useful context beyond the annotations, but it does not explain operational implications such as whether the call blocks, returns an ID to poll, or how to check completion status.

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 ten-word sentence with zero wasted words. The verb 'Create' is front-loaded, followed by the resource and scope, and the '(long-running)' caveat is appended efficiently without bloating the description.

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 simple 3-parameter tool with 100% schema coverage, annotations, and no output schema, the description covers what, where, and a key behavioral trait. However, the 'long-running' flag raises an unanswered question: how does the agent determine when creation has completed or succeeded? No polling/status mechanism is suggested, which is a notable gap given the explicit latency warning.

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 all three parameters are already documented in the schema. The description's phrase 'in a workspace' reinforces the role of workspaceId, but it adds no format details, constraints, or relationships between parameters beyond what the schema provides, so the baseline of 3 applies.

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 states a specific verb ('Create'), resource ('ML experiment'), and scope ('in a workspace'), which clearly identifies the operation. It distinguishes itself from sibling tools like ml_experiment_list, ml_experiment_get, and ml_experiment_delete through the create verb and resource naming, though it relies on the resource name rather than explicit differentiation.

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 no guidance on when to use this tool versus alternatives such as ml_model_create, ml_experiment_update, or ml_experiment_list. There is no mention of prerequisites (e.g., the workspace must exist) or conditions that would make a different tool more appropriate, leaving selection entirely to inference.

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