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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses the long-poll duration (~20s), termination conditions (timeout, max iterations), possible exit states, and included response fields. This is rich behavioral context the annotations do not provide.

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 dense sentences with the primary behavior front-loaded, followed by termination states and response contents. Every clause carries useful information; no filler or redundancy.

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 polling tool with one required parameter and no output schema, the description explains the wait period, all possible resolutions, and the included response fields. It could be slightly more complete about how the decisionId is used or how changes_requested should be handled, but it is largely sufficient.

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 67%, and the required decisionId parameter has no description in the schema. The tool description does not mention any parameter, failing to compensate for the undocumented and required decisionId. It adds no meaning beyond the schema for the other fields.

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 long-polls until a decision leaves pending_review and enumerates possible outcomes, giving a concrete verb and resource. It does not explicitly differentiate from the sibling tool await_decision, which appears to serve a similar purpose, so it stops short of a 5.

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?

Usage context is implied: the description mentions 'regenerate + continue_decision' for changes_requested, hinting at a follow-up workflow. However, it never explicitly says when to use this poll versus alternatives like await_decision, nor provides exclusions or prerequisites.

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