Wait for something to happen

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

Annotations only declare idempotentHint=false and destructiveHint=false; the description adds substantial behavior the agent could not infer: the server holds the event stream open across turns, timeouts lose nothing, the timeout is deliberately short because re-waiting is free, results are returned in order up to and including the match, and unemittable types are rejected immediately rather than waited on. This is exactly the kind of non-obvious context that prevents misuse.

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 core purpose is front-loaded in the first sentence and each subsequent sentence carries real information (event types, stream persistence, timeout rationale, exclusions). It is on the long side and revisits the 'call again / nothing is lost' idea twice, but there is little pure filler.

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?

With no output schema and only weak annotations, the description carries the full burden and does so: it explains what is returned (all events up to the match, in order), how state persists across calls, how timeouts behave, and what the tool is not for. An agent has everything needed to call it correctly.

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 already 83%, so the baseline is 3, but the description meaningfully extends it: 'pass none to wait for the next thing of any kind' clarifies the types parameter's empty case, and it explains the pid/targeting logic and why a short timeout is safe. It stops short of restating the since cursor and limit semantics, which the schema already covers.

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 and resource — 'Block until the computer reports something' — and immediately frames it as the replacement for polling/screenshotting loops. It enumerates the event types it matches, which pins the scope precisely and separates it from siblings like poll_events, wait, wait_for_computer, and wait_for_file_change.

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?

Gives explicit when-to-use (waiting for window/process/power/clipboard/file events) and explicit when-not-to-use ('Do not use it to wait for a click to land or a page to paint ... a screenshot is still how you find out what the screen looks like'). It also names the alternative behavior it replaces (screenshotting in a loop), so routing is unambiguous.

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