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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new context: the call is free, and only runs made with your own key are visible — a real visibility constraint an agent could otherwise trip over. It also names what the response contains.

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 short sentences, front-loaded with purpose, followed by the status vocabulary, return shape and the visibility caveat. Nothing is redundant or padded.

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?

There is no output schema, so the description correctly compensates by naming status values, the output field and the cost object shape ({usd, idr}). The only missing element is guidance on repeated polling versus one-shot retrieval for a run still in progress.

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 100% and the run_id property already carries a format example, so the baseline is 3. The description adds only the provenance of the ID (returned by run_tool), which is useful routing context but not additional parameter semantics.

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 and resource ("Fetch the status and result of a third-party tool run") and explicitly ties the resource to the sibling that creates it ("started by run_tool"). An agent can immediately distinguish this from run_tool, inspect_tool and discover_tools.

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 tie to run_tool plus the enumerated statuses (running, completed, failed) make the intended flow clear: call this after run_tool, and re-check while status is running. It stops short of explicitly saying to poll until terminal state, and no exclusion/alternative path is named.

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