evaluate_web_task

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

With no annotations, the description carries full burden. It discloses the tool launches a browser, shows the browser by default (headless=false), can save as a recorded flow via save_as_recorded_flow, and captures specific evidence types. It could further mention side effects, resource usage, or auth prerequisites, but covers the major behaviors well.

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?

Structured with an opening summary, 'Args' list, and 'Returns' section. Although lengthy, every line adds value for a 9-parameter tool, and the front-loaded purpose sentence lets an agent quickly identify the tool's role.

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 no output schema and no annotations, the description is remarkably complete. It covers the input parameters, return value fields, and a key usage scenario (one-shot evaluation). The description fully compensates for the missing structured metadata.

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 provides no descriptions (0% coverage), but the description documents all 9 parameters with meanings and defaults. It adds critical semantics like capture options, format choices, and the save_as_recorded_flow behavior, fully compensating for the schema gap.

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 runs a browser agent for a natural-language task and returns a rich evaluation report. It specifies the resources (URL and task) and distinguishes it from sibling tools like record_test_flow by framing it as a one-shot evaluator.

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?

Provides clear context: use for one-shot evaluation without prior recording, explicitly noting 'No need to discover/record/replay first.' While it implies alternatives like record_test_flow, it does not explicitly name alternatives or say when not to use this tool, so it falls just short of full guidance.

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