wait

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

With no annotations, the description carries the full behavioral burden. It usefully discloses a hard cap ('Max 30s'), which is real behavior the agent could otherwise only discover by failure, but it doesn't say whether the call blocks, whether values over 30s are clamped or rejected, or what the result contains.

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?

Two short sentences, front-loaded with the verb and followed by the concrete use case. Minimal waste; the only slight ambiguity is what 'Max 30s' means operationally.

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 sleep with an output schema, this is nearly sufficient, but the missing overflow behavior and the unmentioned relationship to `wait_until_idle` leave real gaps given that sibling exists.

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?

The only parameter has 0% schema description coverage, so the description must compensate. 'Max 30s' does add a meaningful bound the schema lacks, but the units/type semantics and overflow behavior for `seconds` remain unstated.

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?

States a specific action (sleep) with a concrete motivating example (waiting for an app to load before a screenshot), so the agent knows exactly what it does. It does not distinguish the tool from the sibling `wait_until_idle`, which is the main alternative for the same need.

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 example implies when to use it (fixed pause before screenshotting), but there is no explicit guidance on when to use it versus `wait_until_idle`, nor any exclusion (e.g. 'prefer wait_until_idle if you need to wait for actual idle state').

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