cortex_optimize

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

With no annotations, the description carries the full burden. It transparently discloses pricing per mode, the charging formula (max(list, provider cost x 2.0)), and the asynchronous nature via job_id. It doesn't address failure handling or authentication, but the pricing and workflow transparency are strong.

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?

Three concise sentences with no filler. The first sentence states purpose and return type, the second provides pricing, and the third gives usage guidance. Perfectly front-loaded and efficient.

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?

Covers purpose, pricing, mode guidance, and the need to poll with cortex_get_job. Although there's no output schema, the description clearly indicates the return of a job_id. It lacks details on error handling or response format, but for a compute submission tool, the essentials are covered.

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 descriptions cover all parameters (100% coverage), so baseline is 3. The description adds meaningful value by mapping prices to the mode enum and recommending auto unless quantum is needed, which helps users choose the correct mode.

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 solves QUBO/Ising optimization problems and returns a job_id for polling. It distinguishes itself from siblings like cortex_get_job (polling) and cortex_estimate_optimization (estimation) by explicitly mentioning the solve and job_id.

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 explicit guidance on mode selection ('Use mode=auto unless you specifically need quantum') and directs users to poll with cortex_get_job. However, it doesn't mention when to use cortex_estimate_optimization instead of this tool, leaving some ambiguity for cost estimation workflows.

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