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

Goes well beyond the readOnly/idempotent annotations: it explains that cost_micros is provisional while billing_pending, that results carry cost_final/cost_note, and — critically — that for a zero-data-retention run the first read of a finished run returns the output and then deletes it, a one-shot side effect an agent could not infer from destructiveHint=false. This is exactly the kind of context annotations cannot carry.

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?

The cost caveat is front-loaded and the zero-data-retention warning follows logically; most sentences earn their place. The closing sentence on run fees, per-second compute and provider pricing is somewhat tangential for a read tool and largely defers to GET /v1/me anyway.

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?

No output schema exists, so the description must describe the return shape — and it does, naming status, output, error, cost_micros, billing_pending, cost_final and cost_note. Combined with the single fully-documented parameter and safe-read annotations, an agent has everything needed to call it correctly.

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?

There is a single id parameter at 100% schema coverage, and the description adds no meaning beyond it (no format, prefix, or provenance detail not already in the schema). With the schema doing the work, baseline 3 applies.

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?

Opens with a specific verb+resource and enumerates exactly what is returned: status, output, error, cost, billing_pending. It is clearly distinguishable from list_runs, though it never names the obvious sibling wait_for_run, which an agent might otherwise prefer over re-polling.

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 when-to-act guidance for the cost field: quote only when cost_final is true, otherwise re-call get_run in a few seconds. It does not, however, tell the agent when to use this versus wait_for_run for a run that is still going, leaving the main alternative unaddressed.

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