Wait

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

With no annotations, the description carries the full burden; it does disclose that the call blocks for the duration and hints at the cost via "use sparingly". It omits the upper bound (60s cap, only in the schema) and says nothing about whether the delay blocks the session or other calls, which matters for a sleep tool.

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?

A single front-loaded sentence with the core action first and the guidance in a tight parenthetical. Nothing is wasted and no reading is required beyond the first clause.

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 one-parameter sleep with no output schema and no annotations, the description covers what it does and when it is appropriate. The missing piece is the relationship to wait_for_window, which would prevent a badly chosen polling sleep.

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?

One parameter with 0% schema description coverage, so the description must compensate. It clarifies the unit (milliseconds), which the parameter name alone only implies, but adds nothing about the 0–60000 range or what happens at the boundary.

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 verb+resource: sleeps for a given number of milliseconds, which is unambiguous about what the call does. It does not distinguish itself from the sibling wait_for_window, which is the closest functional alternative an agent will consider.

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?

"Use sparingly, e.g. after launching an app" gives one concrete when-to-use case plus a caution, which is more than nothing. However, it never names wait_for_window — the sibling that should be preferred when the agent is waiting for a window to appear — so the key routing decision is left to inference.

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