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

Goes well beyond the readOnly/idempotent/destructive annotations by disclosing that results are final only when phase is "done", and that partial/failed runs return partial findings plus a message. This is exactly the operational behavior an agent needs to avoid acting on incomplete data.

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?

Purpose is front-loaded, but much of the text enumerates return fields (resultsMarkdown, prioritizedIssues[], quickScan) that an output schema already documents, which the rubric treats as unnecessary. Dense and somewhat repetitive against the structured contract.

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?

The behavioral gaps (phase finality, partial/failed semantics) are covered and return values are backed by an output schema. The only real omission is any guidance on the required testId, so it is complete but not exhaustive.

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 single parameter testId has 0% schema description coverage and the description never mentions it or how to obtain a value. With low coverage the description is expected to compensate and it does not, though the parameter is largely self-evident.

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+resource ("Returns the usability results for a test") that cleanly separates it from get_test_status (status) and wait_for_results (blocking). An agent can identify the tool without opening the schema, and the sibling it is not is named.

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?

It names wait_for_results and the condition that distinguishes them ("returns the same data once a test finishes"), implying this fetches the current snapshot. It gives no explicit when-not/when-to instruction or prerequisite phrasing, so routing is clear but not fully spelled out.

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