Reverse crosswalk

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds one genuinely useful behavioral fact — that the cross-framework results are derived indirectly through the CORF hub rather than direct pairwise mappings — but says nothing about coverage limits, missing mappings, or latency.

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?

One sentence, front-loaded with the starting point and input formats, then the output. No filler or redundant restatement of the tool name.

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?

With no output schema, the description correctly spends its words on return semantics — mapped CORF areas plus the other two frameworks' statements — so an agent knows what it will get back. It stops short of describing the shape of that output (grouping, field names, markdown vs json rendering differences).

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 coverage is 75% and the enum values are self-describing, so the schema carries most of the load. The description adds real meaning by showing the expected reference format for each framework ('A.5.19' for ISO, '8.4' for PCI, '2.9' for SWIFT), which the schema's generic 'Reference id in that framework' does not.

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 and resource: given a framework reference (ISO/PCI/SWIFT), return the mapped CORF areas plus the other two frameworks' statements. The examples ('A.5.19', '8.4', '2.9') make the operation concrete. It implies the inverse direction of the sibling corf_crosswalk but never names it, so sibling differentiation is left to inference.

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 opening 'Start from an ISO 27001 control...' clearly establishes the entry-point condition that selects this tool over a forward crosswalk, and the parenthetical '(derived through the CORF hub)' signals it is a lookup rather than a raw mapping. No explicit when-not or named alternative is given, so it falls short of a 5.

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