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

Annotations already establish readOnlyHint/idempotentHint/destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the polling contract, that wait is capped at 25, and that the call returns as soon as a running test finishes. It omits auth requirements for guest_token.

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?

Front-loaded with the result states, which is good, but the wait/long-poll behavior is stated twice in near-identical sentences ('With wait (up to 25) it answers as soon as a running test finishes' and 'Long-poll: with `wait` the answer comes as soon as...'). The redundancy costs it a point.

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?

No output schema exists, so the description carries the return-value burden and does so by enumerating the result states and their payloads. Combined with the polling contract, an agent has enough to call it correctly; the unexplained guest_token is the only notable gap.

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 schema already describes id and wait's 0-25 range. The description goes further by explaining wait's actual effect (long-poll resolution semantics), which is genuine added meaning. guest_token remains undocumented in both schema and description.

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?

Names a specific resource (lab tests of an audit) and enumerates the possible result states (running, finished with scores/metrics/savings, failed). An agent can tell what it returns, but it never distinguishes itself from the sibling lab_test, which is the most likely confusion point.

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?

Provides useful operational guidance ('Repeat until it is not running') and explains the long-poll pattern, which implies when to call it repeatedly. However it never states when to use this versus lab_test, nor any prerequisite like a completed audit, so routing guidance is only implied.

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