find_ui_elements

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

No annotations are provided, so the description must fully disclose behavior. It only states the prerequisite and search criteria. It does not describe return format, whether it is blocking, performance implications, or behavior when no elements are found. The red emoji hints at caution but lacks substance.

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 a single sentence with an emoji for emphasis, making it very concise. However, it could be better structured by explicitly listing the search criteria or using bullet points.

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 simple tool with one parameter and no required fields, the description provides the essential prerequisite. However, without an output schema, it should hint at the return type. It lacks information about what UI elements are covered and possible return structures.

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 has 100% description coverage for the filter properties. However, the description mentions searching by 'name' which is not in the schema, potentially misleading. It adds no value beyond the schema and introduces an inconsistency.

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 clearly states the tool finds UI elements in a running game by type, text, or name. However, 'name' is not present in the input schema, creating a mismatch. It distinguishes from sibling tools like find_nodes_by_type by targeting UI elements specifically.

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 includes the prerequisite 'Game must be running' but does not provide guidance on when to use this tool versus alternatives like find_nodes_by_type or find_nodes_by_script. No exclusions or explicit usage context are given.

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