reading_start

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

The annotations already flag destructiveHint=true and non-idempotence, and the description adds genuinely new behavioral facts: the traversal is autonomous, it returns promptly (i.e., asynchronous start), and is cancelled by new input, stop, target or mode changes, but not by chat messages. That cancellation contract is not derivable from the annotations.

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?

Four tight sentences with the action and precondition front-loaded and no filler. Density is high, though the compressed phrasing ('pure pointer traversal', 'target or mode changes') trades some clarity for brevity.

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 complex tool with nested objects, 5 parameters and no output schema, the description omits any parameter guidance and never says what is returned ('return promptly' implies an async handle but does not confirm it). The cancellation model is covered, but the caller still cannot construct a valid call from this text.

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 description coverage is 0% across 5 parameters, including nested segments, rect, direction, duration_ms, pause_policy and threshold_px, yet the description explains none of them. Only an oblique link exists ('explicit client regions' → segments, 'target client' → hwnd), leaving the bulk of the schema undocumented.

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 verb ('Begin') and a concrete resource ('autonomous pure pointer traversal of explicit client regions'), which distinguishes it from the sibling reading_status and reading_cancel tools. 'Pure pointer traversal' is somewhat jargony, but the intent remains recoverable.

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?

It states a hard precondition ('The cursor must already be inside the target client') and constraints ('No buttons or keys'), plus explicitly lists which events cancel the traversal and the one exception (chat messages). It never names reading_cancel or reading_status as alternatives, so it falls short of a 5.

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