wait_change

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

Goes far beyond annotations by explaining the baseline default (screen at call time), hash reuse as next baseline, timeout behavior (returns ok=true with changed=false instead of error), and the exact return object fields. Annotations already indicate read-only and idempotent, but the description adds crucial operational context.

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 sentences, each essential. The description is front-loaded with the main purpose, then logically details baseline semantics, timeout handling, and return fields—no wasted words or repetition.

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?

Despite lacking an output schema, the description explicitly lists the return fields and their semantics, covers timeout and baseline behavior, and gives a usage hint. This makes the tool's behavior fully understandable for an agent to invoke correctly.

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?

With 0% schema coverage, the description compensates by explaining baseline_hash ('pass a prior hash') and timeout_ms ('Timeout is not an error'). The required sid is not described, but it is a common session identifier across sibling tools, so the gap is minor.

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's function: block until screen content changes, then snapshot. It uses a specific verb ('Block until') and resource ('screen content changes'), and explicitly differentiates from sibling wait_regex by noting it can't false-positive on existing text.

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?

Explicitly instructs when to use: 'call it right after send_line/send_keys to wait for ANY change from the baseline.' It also names an alternative (wait_regex) and explains why this tool is better in this scenario, providing clear context and exclusion.

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