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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses the 45-second cap, the immediate-wake mechanism ('wakes immediately through Redis when the user acts'), and the retry contract, all of which an agent needs to use a long-poll correctly. The retry guidance is consistent with idempotentHint=true.

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 short sentences, front-loaded with the action and its bound, followed by the mechanism and the retry rule. No filler or restatement of the tool name.

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 description covers the blocking duration, wake behavior, and retry semantics, and an output schema exists so return values need not be explained. Nothing an agent needs in order to invoke this 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 coverage is 100% and the schema already explains that approval_id comes from request_approval. The description adds the operationally important detail that retries must reuse the same ID, which the schema does not convey. With only one well-documented parameter, this is a modest but real addition.

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 states a specific verb+resource ('wait ... for a pending approval'), the exact bound ('up to 45 seconds'), and implicitly distinguishes itself from the polling sibling get_approval via 'without polling the database'. An agent can tell what this does and how it differs from the other approval tools.

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 gives a clear usage context (waiting on a pending approval) and an explicit follow-up rule: 'If the result remains pending, call this tool again with the same ID.' It gestures at the alternative ('without polling the database') but never names get_approval or states when not to use this tool.

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