find_by_external_reference

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds valuable behavioral detail beyond annotations: matching is case-insensitive, ignores punctuation, and the framework filter is optional. This meaningfully helps an agent predict results without contradicting 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 front-loaded with the core purpose, then provides concrete examples and behavioral caveats. Every sentence adds value: the examples disambiguate key formats, and the matching rules prevent incorrect expectations. It is appropriately sized for a tool with two parameters and nuanced matching behavior.

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 output schema already covers return shape, the description does not need to explain return values. It covers the tool's purpose, supported key formats, normalization behavior, optional framework restriction, and points to the authoritative list. For this complexity level, nothing essential 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 input schema offers only generic titles ('Key', 'Framework') with 0% schema description coverage, so the description must carry the semantic burden. It fully compensates by explaining that 'key' is an external reference identifier with concrete examples and that 'framework' restricts results to a framework name from list_reference_frameworks. Both parameters are meaningfully clarified.

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 opens with 'Reverse crosswalk' and immediately states the exact resource ('AIGF risks and controls') and action ('find ... that cite an external reference'). The examples clarify the input format and the phrase 'reverse crosswalk' distinguishes it from mapping tools like map_control_to_external.

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 context for when to use the tool: when you need to find risks/controls by an external reference. It also directs the user to list_reference_frameworks for valid framework names. However, it does not explicitly mention exclusions or contrast itself with search_framework or map_control_to_external, so it stops short of a perfect 5.

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