wait_until

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

Beyond annotations (readOnlyHint=true), the description discloses critical behavioral traits: it blocks the main thread, has a hard time limit to avoid stalling the editor's pipeline, and returns a retry signal. This is exactly the kind of context needed for an agent to invoke it safely.

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?

Three dense sentences convey purpose, behavior, retry guidance, and allowed values without redundancy. The most important information ('Wait for a condition') is front-loaded, and every sentence earns its place.

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?

The tool is simple, with annotations and no output schema. The description covers condition types, blocking semantics, and retry behavior. The only notable omission is the meaning of `timeout_ms`, which prevents a perfect score.

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 schema has 0% description coverage, so the description must compensate. It fully explains the `condition` parameter with allowed values, but never explains `timeout_ms` or how it relates to the stated ~1.5s limit. Partial compensation earns a 3.

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's function: 'Wait for a condition,' and enumerates the exact valid condition values. This unambiguously distinguishes it from siblings like wait_for_node, which presumably waits for a node, and get_play_state, which polls state without blocking.

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 provides explicit invocation context: it blocks up to ~1.5s and returns 'not yet' if the condition isn't met, instructing the agent to call again. It doesn't explicitly name alternatives, but the condition choices and behavior make intended usage clear relative to sibling tools.

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