wait_text

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that it 'Returns instantly on match,' which is a positive-case behavior, and implies blocking via 'Replaces blind sleeps.' However, it does not disclose timeout behavior (e.g., what happens if the text never appears) or any side effects. The description covers the core operation but omits failure semantics, which is a notable gap for a wait operation. Thus a 3 is appropriate.

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 description is extremely concise and well-structured. The first sentence states the core function, the second provides usage context, and it front-loads the most important information. Every sentence earns its place; there is no fluff or redundancy. This is a model of efficiency for a tool description.

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 that there is an output schema (not shown but flagged as true), return values need not be described. However, the tool has six parameters and zero annotation coverage, and the description only partially explains usage scenarios. It lacks parameter semantics and timeout behavior, which are essential for correct invocation. While the usage guidance is helpful, the overall completeness is moderate, leaving agents with unanswered questions about region, monitor, and timeout handling. A 3 is appropriate.

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%, meaning the description must explain the parameters, but it does not. It implicitly mentions the target (text to wait for) but fails to explain region, window, monitor, timeout, and disappear. The only hint is 'appear (or disappear)' which maps to the disappear parameter, but it's not explicit. With six parameters, the description adds minimal value beyond the schema, leaving agents to guess the meaning of most parameters. A score of 2 reflects this significant 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's purpose: 'Wait for on-screen text to appear (or disappear).' It specifies the action (waiting), the resource (on-screen text), and the optional disappearance condition. It also adds context that it 'Replaces blind sleeps,' which helps differentiate it from more primitive approaches. While it doesn't name sibling tools, the unique behavior of text-waiting is unambiguous.

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 provides explicit usage guidance: 'Use for in-window state no compositor event covers: button flips (UPDATE→PLAY), page content, dialogs.' This gives concrete scenarios where this tool is appropriate, implying it's for cases where compositor events (e.g., wait_window) won't fire. It doesn't explicitly list when not to use it, but the examples and the 'no compositor event covers' condition are strong enough to route the agent. A score of 4 is warranted because it lacks explicit alternative names but the context is clear.

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