compare_kernel_validation

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

Annotations already cover the safety profile with readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral scoping by emphasizing 'immutable' cohorts and 'exact' correctness metrics, which goes beyond the annotations. No contradiction is present.

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?

The description is a single front-loaded sentence that begins with the action verb and contains no filler or redundant phrasing. Every word contributes to the tool's purpose or preconditions.

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 an output schema and strong annotations, the tool's request schema contains a complex protocol object that the description never mentions. An agent would struggle to know how to build a request or choose this tool over several closely related comparison and recording siblings.

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, but it only rephrases the notion of two cohorts, loosely mapping to baseline_run_set_id and candidate_run_set_id. It provides no guidance for the optional protocol object, experiment_id, or how to construct a valid comparison request.

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 clear verb ('Compare'), a defined resource ('exact correctness metrics'), and a precise scope ('two immutable run cohorts'). This makes the tool's purpose recognizable and distinguishes it from generic run comparison tools, though it does not explicitly name a sibling.

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 phrase 'from two immutable run cohorts' implies a prerequisite about which run sets are valid, and 'exact correctness metrics' gives some sense of when it applies. However, there is no explicit guidance about when to prefer this tool over siblings like compare_run_sets, record_kernel_validation_comparison, or extract_kernel_validation.

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