browser_pull

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does convey the core behavior of adopting the builder's plan and capturing hand edits, but it does not state whether this overwrites the current working plan, whether it is destructive, what it returns, or whether it affects the builder's state. For a state-synchronizing operation, these are material gaps.

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?

A single compact sentence delivers the core meaning, with the clarifying parenthetical adding the crucial context about hand edits. There is no filler or redundancy, and the primary action is 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?

For a zero-parameter tool with no output schema and no annotations, the description adequately states the main operation and rationale. However, it leaves undefined terms like 'builder' and 'window', and it does not clarify the relationship to sibling tools such as browser_push or browser_readback, so an agent may still be unsure about exact behavior and return values.

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 tool has zero parameters, so the description is not required to explain parameter details. The baseline of 4 applies because there is no parameter documentation burden to satisfy.

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 names a specific action ('Adopt') and resource ('the working plan') and identifies the source (what the builder currently holds). It also adds the key purpose 'captures hand edits made in the window', which differentiates this pull-style tool from push-style siblings. The jargon 'builder' and 'window' is somewhat undefined, but the direction and intent are discernible.

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 when to use the tool: when you want to bring the builder's current plan into the working plan, especially after manual window edits. However, it provides no explicit guidance about when not to use it or how it compares to siblings like browser_push or browser_readback.

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