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

Annotations cover read-only and idempotent safety; the description adds meaningful behavior by revealing long-polling semantics, the expiry condition, and that the result contains status plus the chosen option once decided. It does not contradict annotations and does not overstate side effects.

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?

Two concise sentences, front-loaded with the key behavior and return info, with no redundant filler. 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?

With the fully described schema, read-only annotations, and an output schema, the description completes the picture by naming the polling behavior, stopping condition, and returned status/option. No critical operational details are 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%, so the parameters timeout and approval_id already have descriptions. The tool description adds context about decision/expiry, but it does not enrich the parameter semantics beyond what the schema provides; baseline 3 is appropriate.

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 ('Long-poll an approval request') and specifies the termination conditions ('until the human decides or it expires'). It also states the return value, making it easy to distinguish from get_approval and the other wait_for_* siblings.

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?

'Long-poll...until...' clearly frames when to invoke: use this when you want to block until an approval decision or expiry. However, it does not explicitly tell the agent to prefer get_approval for a non-blocking read, so no exclusions are named. This is clear context but lacks explicit alternatives.

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