wait

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

With no annotations, the description carries the full burden of disclosing behavior. It explains what 'stable' does, but does not mention timeout behavior, error handling, or whether the operation is read-only. It adds some behavioral context beyond the schema, but leaves significant gaps for a tool with 35 parameters and no 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?

The description is two sentences, front-loaded with the core action, and each word adds value. It efficiently conveys the main behavior and the key mode distinction without unnecessary verbosity.

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 the tool's complexity (35 params, no annotations), the description is adequate but incomplete. It covers the primary wait modes but omits details about timeouts, default behavior, and what the result contains. An output schema exists, so return values are covered elsewhere, but the behavioral boundary conditions remain undocumented.

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 69%, so the description is expected to add some semantic value. It maps the 'kind' parameter to text/ref/selector/stable and explains the difference between a specific readiness condition and a stable UI wait. However, it does not elaborate on timeoutMs, durationMs, quietMs, or other parameter interactions, leaving the agent to infer from parameter names.

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 waits for a duration, text, snapshot ref, selector, or stable UI. It provides a specific verb and resource, and the multiple wait modes distinguish it from sibling tools like 'get' or 'snapshot'. No other sibling offers the same waiting behavior.

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 gives direct guidance on when to use each mode: 'Use text, ref, or selector for a specific readiness condition; stable waits until the UI stays quiet for the requested window.' This clarifies the intended context of use, though it does not explicitly mention alternative tools or exclusions. Still, it provides clear usage context.

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