list_rules

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

Annotations only cover readOnly/idempotent, but the description adds substantial behavioral context: fully offline (no network, no API key, no stored credentials), no writes outside the process, returns no PASS/FAIL or SAFE/RISK verdict, and that `total` is post-filter. This is exactly the extra context annotations cannot carry.

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?

Dense and front-loaded, with the discovery role and usage routing early. Slightly heavy: the GLOBAL-token caveat and the read-only/idempotent claim each appear more than once, and the leading 'EU AI Act Article 5 and Article 50' fragment reads like a topic tag rather than a usable statement.

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?

An output schema exists, so return values need not be explained, yet the description still notes the returned fields and the meaning of `total`. For a single-optional-param discovery tool, nothing an agent needs to call it correctly 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?

Schema description coverage is 100% and the schema already defines the enum, the omit-to-list-all behavior, and the GLOBAL-is-not-EU∪US caveat. The description restates those same facts rather than adding syntax or edge-case meaning, so baseline 3 applies.

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?

States a specific verb (list) and resource (TrustLint offline compliance rules in the ComplyEdge corpus) and explicitly positions itself as a discovery tool. It names sibling boundaries directly: not the hosted policy engine, not a system classifier, and distinct from check_compliance's evaluation role.

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?

Gives an explicit when ('scope a jurisdiction before calling check_compliance') and an explicit when-not ('do not use it to evaluate text'), naming the sibling to use instead. The continuation instruction to pass the same jurisdiction token into check_compliance closes the loop completely.

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