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

Annotations cover safety (readOnly, idempotent, non-destructive, closed-world). The description adds genuine behavioral context beyond them: it returns three distinct fields (status, result, error) and is designed for repeated polling until completion. It does not mention rate limits or retry cadence, so not a 5.

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 tightly written sentences with the core purpose front-loaded and no filler. Every clause carries information (what is returned, where the id comes from, how to use it).

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?

An output schema exists, so return values need no elaboration, and annotations already carry the safety profile. For a simple two-param read tool the description is nearly sufficient, with the only gap being the unexplained `authorization` parameter.

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 0% for two required params, so the description carries the burden. It hints at operation_id's provenance (the `Location` of a `202` from `complete_billing`) but gives no format details, and `authorization` is never addressed. It only partially compensates for the coverage gap.

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?

States a specific verb and resource: return status, result and error of an operation the caller started. It also anchors the resource to a concrete sibling (the `202`/`Location` from `complete_billing`), so an agent can place it precisely among the 30+ 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?

Gives explicit usage context: 'Call this to poll it to completion,' which tells the agent this is the polling endpoint for previously started async work. It does not name when NOT to use it or any alternative tool, but none of the siblings serves the same polling role.

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