measure_interaction

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

Without annotations, the description carries full burden. It discloses that the tool clicks, waits for a condition, and returns timing. However, it does not mention potential timeouts, error handling, or whether it modifies session state (e.g., interaction logs).

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 sentences front-load the action and condition, then state the return value. No extraneous text; every sentence adds value.

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?

The description covers the core functionality and return value, but lacks details on timeout behavior, error scenarios (e.g., element not found), or interaction with other session state. Given no output schema, the description is mostly complete but could be more robust.

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 descriptions already provide 100% coverage for parameters. The description rephrases the wait_for parameter behavior (default networkidle) but adds no new semantic information beyond what the schema states.

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 action: click an element and measure time until a condition (networkidle or selector appears). It includes the return value (timing in ms), making it distinct from sibling tools like click_element or wait_for_network.

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 implies usage for timing interactions but does not explicitly differentiate from similar tools like interact_and_test or provide when-not-to-use guidance. No alternatives or exclusions mentioned.

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