wait

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

With no annotations, the description carries the full disclosure burden. It usefully states the blocking sleep behavior and the 60-second ceiling, but leaves open whether a value over 60 errors or is clamped, and whether the call blocks the whole session or just the agent loop.

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?

One sentence, front-loaded with the verb and the hard constraint, then the rationale. Nothing is padded and nothing important is buried.

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 trivial one-parameter timing tool with an output schema present, the description covers what the tool does, why, and its safety ceiling. The only real gap is the over-limit behavior, which is minor for this complexity level.

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 0%, so the single 'seconds' parameter is undocumented in the schema apart from a default of 1. The description partially compensates by stating the 'max 60 s' bound, but it never names the parameter or says what unit granularity (fractional?) is accepted.

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 gives a specific verb ('Sleep') plus the reason it exists: letting deferred GUI actions finish before the next observation. It is unambiguous and clearly distinct from action-oriented siblings like click_widget or trigger_action, though it doesn't explicitly contrast itself with them.

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?

'...so deferred GUI actions can finish before the next observation' tells the agent the situation that selects this tool: an observation follows an action that needs time to settle. No exclusion or alternative is named, but none is really needed for a single-purpose sleep tool.

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