ui_step

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

With no annotations supplied, the description carries the full burden and does disclose the key behavioral trait: the label scopes the report grouping and persists "until the next ui_step." It also conveys that this is an annotation rather than a page action and that the label is "the only human-readable description the report has." It stops short of saying what the call returns or what happens if it is called outside an open session.

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 core instruction is front-loaded in the first sentence, and the grouping rule follows immediately. The examples and the "write it for the person who will read the result" clause each add distinct guidance rather than restating the schema, though the final clause is slightly repetitive of the opening "in plain language."

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 two-parameter, fully documented labeling tool with no output schema and no annotations, the description covers purpose, timing, grouping scope, and authoring style. Only minor details (return value, behavior when no session is open) are left to the schema or unstated, which is acceptable at this complexity.

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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning for the label parameter beyond the schema's "Short description of what this step verifies or does": write for the report reader, not for yourself, and keep it tied to the intent of the step. The session_id parameter is not discussed in the description, but the schema documents it fully.

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?

"Label what you are about to do, in plain language" states a specific verb (label) and the exact effect: every following action is grouped under this label in the report until the next ui_step. That grouping semantics clearly separates it from the action siblings (ui_click, ui_fill, ui_navigate), which perform page operations rather than annotate the report.

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?

"Call it before each meaningful part of the flow" plus three concrete examples ("Log in as jcarlin", "Toggle Manual Invoice access on", "Reload and confirm it persisted") give a clear trigger condition. There are no explicit exclusions or when-not guidance, and no alternative tool is named, but this is a unique labeling tool so the absence of alternatives is not a real gap.

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