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

Annotations already establish non-read-only, idempotent, non-destructive behavior. The description adds meaningful context beyond them: the operation is asynchronous ('Does not complete immediately: a real human performs the test'), requires authorization, demands a stable idempotency_key, and involves no payment. It omits failure modes and rate-limit behavior.

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?

Six short sentences, none wasted, with the core action front-loaded and the async/no-payment constraints following in priority order. No filler or restatement of the tool name.

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 5-parameter, non-destructive mutation tool with no output schema, the description covers the key agent needs: authorization, idempotency stability, async human execution, and absence of payment. It leaves the 'context' parameter and the no-slot-available path unexplained.

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?

With only 20% schema description coverage, the description must carry the burden. It adds real meaning for idempotency_key ('stable', beyond the schema's min/max length) and partially for tasks and device, but repeats what the schema already encodes (maxItems 3, desktop/mobile enum) and says nothing about the 'context' parameter.

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 precise verb (queue) and resource (human usability test request) and scopes it to 'a public website you own or are authorized to test.' This is clearly distinguishable from siblings like get_test or cancel_test, which read or cancel rather than create a queued request.

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 concrete constraints for use (up to three tasks, desktop or mobile, no card or checkout, requires authorization) and notes the request enters the queue immediately if a slot is available. It stops short of explicitly naming join_waitlist as the alternative when no slot is available, leaving that inference to the agent.

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