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

No annotations are provided, so the description carries the full burden. It discloses that the call is 'Free' and enumerates return fields, but it does not explicitly state this is a non-mutating read operation, nor does it cover rate limits, error scenarios, or job lifecycle concerns. Some useful context is present, but gaps remain.

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?

A single sentence with no filler. The key verb and purpose are front-loaded, and each clause adds value: 'by id' specifies input, 'Free' notes cost, and the return list sets expectations. This is exemplary conciseness.

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 simple one-parameter polling tool without an output schema, the description is sufficiently complete. It identifies the source of the ID (via schema), states the return content, and fits well within the sibling workflow. No critical information is missing.

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 description coverage is 100% because job_id is fully described as 'Job id from cortex_optimize'. The tool description adds no additional meaning about the parameter, so a baseline of 3 is appropriate since the schema carries the semantic load.

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 uses a specific verb 'Poll' with a clear resource ('optimization job by id') and explicitly lists what is returned (status, solution, objective, error). This distinguishes it from siblings like cortex_optimize (which creates jobs) and cortex_list_backends (which lists backends).

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?

The description clearly implies the tool is for checking the status/result of an optimization job, which is unique among siblings. It lacks an explicit 'when not to use' or direct alternative mention, but the polling purpose is self-evident from the description and schema reference to cortex_optimize.

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