Start evaluation

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds meaningful behavioral traits: 'immutable' discloses that the created run cannot be modified, and 'measured' indicates metrics are computed. This goes beyond what the annotations already provide.

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 sentence with no wasted words. The action verb and key qualifiers are front-loaded, making the core operation instantly readable.

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 7-parameter creation tool with no output schema, the description is too thin. It omits what the created run returns, how metric_config and idempotency_key influence behavior, and what 'immutable' means for subsequent operations like updates or deletions.

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%, so the description must compensate. It only adds semantic meaning for model_version_id and dataset_version_id, while leaving the other five parameters (org_slug, task_type, random_seed, metric_config, idempotency_key) unexplained in both the schema and the description.

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 a specific verb ('Create') and a specific resource ('immutable measured evaluation run') and further specifies the two key inputs (model version and dataset version). This clearly distinguishes it from sibling tools like scorestudio_start_training, whose purpose is training rather than evaluation.

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 use for evaluation runs but gives no explicit when-to-use guidance or alternatives. An agent cannot tell from the description alone when to choose this over scorestudio_start_training or scorestudio_run_workflow; there are no exclusions or context signals beyond the tool name.

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