Run Test Regimen

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

With no annotations provided, the description carries the full burden, and it delivers richly. It discloses the full side-effect chain: loads the model, runs deterministic units inline with a logged param search, moves orchestrator_judged units to pending, unloads exactly once, and writes a registry entry when nothing is pending. It even clarifies the return contract: only pending_unit_ids, never raw output. This is exceptional transparency for a stateful mutation tool.

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?

Three sentences, each earning its place. The main purpose is front-loaded in the first sentence, and the following sentences pack precise behavioral details without filler. The description is dense but not bloated, and every clause adds decision-relevant information.

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?

Despite having no output schema and no annotations, the description is nearly complete for invoking the tool correctly. It explains what the tool does, the order of operations, the side effects (registry write, unload), and the exact return value. The only minor omission is explicit provider parameter guidance, but the core execution model and postconditions are fully specified.

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 gives meaningful context for profile ('profile's registered test units') and model_id ('one model'), but it never mentions the optional 'provider' parameter or explains how it influences the run. The description partially compensates but leaves the third parameter semantically unaddressed.

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: 'Test one model against the profile's registered test units'. It then distinguishes this from sibling operations by detailing the execution pipeline: deterministic units inline, orchestrator_judged units to pending, unloads exactly once, and registry writes. This clearly separates it from tools like validate_test_unit, run_untested_sweep, or load_model.

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 clear context for when the tool is appropriate: when you want to run a full test regimen for one model against a profile's registered test units. It also hints at lifecycle behavior (loads, unloads once) that helps an agent understand the operational context. However, it does not explicitly name alternatives or state when not to use it, so it stops short of full usage differentiation.

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