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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds useful behavioral context: this is a long-poll that waits until the owner approves or denies on their phone. It does not describe timeout or error behavior, but it does add value beyond annotations.

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 short, front-loaded sentences with no filler. The first sentence identifies the action and subject, and the second clarifies the blocking/return behavior.

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 poll tool with no output schema, the description states the return trigger but not the shape of the result, timeout behavior, or how approvalId is obtained. The annotations cover safety and the schema covers the hatchId aliases, but an agent still lacks a few operational details needed to handle the poll cleanly.

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 covers hatchId and tenantId, including the alias relationship, but approvalId has no schema description and the tool description adds no parameter-level meaning. With only 67% schema coverage and no compensation in the description, the required parameter remains underspecified.

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 ('Poll'), a specific resource ('pending Tier-2 phone approval'), and the expected outcome ('Returns the result once the owner approves or denies'). This clearly distinguishes the tool from generic polling siblings by tying it to the phone-approval flow.

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 implies the right context: call when an approval is pending and the owner has not yet decided. However, it does not explicitly name alternatives like poll_decision or await_decision, nor does it state when not to use this tool, so usage guidance is only implicit.

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