feature_separate_batch_eval_run

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

No annotations are provided, so the description carries the full behavioral burden. It implies network access ('explicit network-scope confirmation'), but says nothing about whether the run mutates state, how long it takes, whether it can be repeated, or what permissions are needed — significant gaps for a tool that triggers an evaluation run.

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 eight-word sentence is compact and front-loads the outcome, but the brevity comes at the cost of missing information rather than being efficient. It is short, not pointed.

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?

With three parameters at 0% description coverage, no annotations, and no parameter guidance in the description, an agent cannot reliably construct a call. The output schema is present so return values need not be described, but the input side is left almost entirely undocumented.

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 and does not. 'Network-scope confirmation' loosely gestures at allow_network, but cohort_id (required) and minimum_support (default 10) receive no explanation of format, meaning, or impact anywhere.

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 phrase 'Discover batch-only issues' names an outcome but not a concrete verb+resource pairing, and 'batch-only' is not defined. With four sibling tools (status, tag, check, insights) that all operate on the same batch-eval feature, the description does nothing to distinguish this 'run' tool from the others.

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?

'After explicit network-scope confirmation' implies a precondition and hints at ordering, but it never states when to choose this tool over check, insights, or status. No exclusions or alternatives are given, so the agent must guess the sequencing.

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