list_drift_alerts

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context: it's a 'discovery tool' that returns 'precomputed drift results' and does not 'fall back to on-the-fly computation,' which clarifies its read-only and static nature. However, it doesn't mention potential limitations like rate limits, authentication needs, or what happens if no data exists, leaving gaps in transparency for a tool with no annotations.

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 appropriately sized and front-loaded: the first sentence states the purpose, the second adds behavioral context, and the Args section efficiently details parameters. Every sentence earns its place with no wasted words, making it easy to scan and understand quickly.

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?

Given the tool's complexity (3 parameters, no annotations, no output schema), the description is somewhat complete but has gaps. It covers purpose, usage context, and parameter semantics well. However, without annotations or an output schema, it doesn't describe return values, error handling, or other behavioral traits like data freshness or access permissions, which are important for a discovery tool with no structured safety hints.

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?

The description adds significant meaning beyond the input schema, which has 0% coverage. It explains each parameter's purpose: model_id filters to a specific model or all models, severity filters by levels ('none', 'moderate', 'severe'), and run_id filters to a specific batch run. This compensates fully for the schema's lack of descriptions, providing clear semantics for all three parameters.

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 clearly states the tool's purpose: 'Browse batch drift findings across features and models' and 'Returns precomputed drift results from the result store.' It specifies the verb ('browse'), resource ('drift findings'), and scope ('across features and models'), making it distinct from siblings like detect_drift or detect_feature_drift. However, it doesn't explicitly differentiate from all siblings, such as list_models or list_skills, which slightly limits its clarity.

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 usage: 'This is a discovery tool — it does NOT fall back to on-the-fly computation.' This implicitly suggests using it for precomputed results and not for real-time detection, distinguishing it from tools like detect_drift. However, it lacks explicit when-not-to-use scenarios or named alternatives, such as comparing to detect_drift for on-the-fly computation, which prevents a perfect score.

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