ATLAS (Adversarial ML)

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

Annotations already mark the tool as read-only and idempotent, and the description adds substantial behavioral context: the distinction between data and tag_pairs, the field names and ranking order, the single_observation:true flag, and the data-quality caveat about 106 total pairs. This goes well beyond the 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 dense but every sentence provides operational value: scope, data field meaning, ranking, the small-n warning, and threshold semantics. It is structured logically and front-loaded with the core resource and purpose.

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 tool with only two parameters and an output schema, this description is unusually complete. It covers the data-quality caveats, field semantics, ordering, and interpretation warnings that an agent needs to correctly use the results. Nothing functionally important is missing.

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 schema already describes both parameters at 100% coverage, but the description adds important semantics for min_cooccurrence: default 2 means the honest set, setting 1 includes single-observation pairs, and those rows should not be treated as true associations. This extra meaning goes beyond the schema descriptions.

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 specific verb ('returns pairs'), a specific resource (MITRE ATLAS technique co-occurrence), and the scope (threats that attack AI/ML systems). It also explicitly distinguishes ATLAS techniques from free-text publish tags, so an agent can tell it apart from general MITRE or threat-search siblings.

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 gives clear on how to interpret results, especially the small-n warning: it tells agents not to report single-observation pairs as associations and that min_cooccurrence=2 is the honest default. It provides clear dataset context, though it doesn't explicitly name alternative sibling tools or when to use them instead.

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