find_classes_implementing_interface

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 genuinely useful behavioral context beyond that: there is no inverse index in the engine, so the call is a full O(loaded classes) sweep with an implied latency cost, plus the returned record shape. That is more than the annotations convey.

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?

Two short sentences: the operation and its cost caveat come first, and the return-shape block follows. Nearly every clause earns its place. Slightly terse on the return fields' meaning (e.g. 'implemented_by_k2'), but the structure is clean and front-loaded.

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?

No output schema exists, but the description supplies the return shape, and the annotations cover the safety profile, so an agent has what it needs to invoke and interpret the call. The remaining gap is modest: no note on how native vs Blueprint implementers affect results, or on the cost of enabling include_blueprints.

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% for both parameters ('interface' resolved via ResolveClass, 'include_blueprints' default true), so the schema already carries parameter meaning. The description adds nothing about acceptable name/path formats or what include_blueprints changes in the result. Baseline 3 is appropriate.

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: 'Enumerate every loaded class that implements a given UInterface.' This is unambiguous and clearly distinct from nearby tools like list_derived_classes or list_objects_of_class, since it is keyed on interface implementation rather than inheritance or class name.

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?

It gives cost context ('No inverse index exists in the engine... O(loaded classes) sweep') and points to a sibling idiom ('same idiom as list_subsystem_classes'), which hints at when the sweep cost is acceptable. But it never states when to prefer this over alternatives such as list_derived_classes or get_class_hierarchy, nor any precondition for the 'interface' argument beyond the schema's ResolveClass note.

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