Wait for an instance

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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds genuinely new behavior: it blocks until a timeout, and it returns found true with the path or found false with the still-missing segment. That return-shape disclosure is valuable since no output schema exists. Polling interval and behavior on mid-wait disconnection are unspecified.

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 tight sentences: purpose, illustrative scenarios, return shape, prerequisite. No filler, and the core verb leads. The prerequisite is last but costs only five words.

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 four-parameter blocking read with no output schema, the description covers what it waits for, when to use it, the failure mode, the return contract, and the connection prerequisite. Nothing needed to call it correctly is missing.

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 description coverage is 100%, with each of path, client, timeout and class_name already documented including defaults and bounds. The description only adds that class_name is optional ('optionally is of a class'), so it mostly restates structured data — baseline 3 applies.

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 opens with a specific verb and resource ('Wait until the instance at a dotted path exists') and adds a class filter, immediately distinguishing it from a one-shot read like inspect_instance. The agent can tell this is a blocking existence check rather than a query of current state.

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?

It names concrete use contexts ('after a teleport or while a map loads') and states the precondition 'Requires the connected state.' It does not explicitly contrast with inspect_instance for the case where the instance already exists, but the timing guidance is clear enough to select correctly.

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