Get results of an earlier data-tool run

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

Annotations already declare readOnly, idempotent, non-destructive, open-world. The description adds genuinely non-obvious context: it does not initiate work and incurs no additional cost, which matters for agent retry/polling decisions. It omits what happens if the run is still incomplete at fetch time and any rate-limit guidance.

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 compact sentence pair that front-loads the core action and follows with the cost/scope reassurance. No filler, nothing redundant with the title.

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?

An output schema exists so return values need no explanation, and the description covers the trigger, scope, and cost profile for a 2-parameter read tool. The one gap is behavior when the run has not finished yet — retry/polling expectations — which an agent polling this tool would want.

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% with both parameters documented and the tool enum fully specified. The description only restates 'by runId and tool name', adding no format, sourcing, or enum semantics beyond the schema, so the 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?

States a specific verb (fetches) and resource (status and results of a run), plus the precise scope: runs that were still 'running' when a data tool returned. This clearly separates it from the run-producing siblings like detect_tech_stack and monitor_website_changes, which the description implicitly contrasts by naming the runId/tool pair.

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 an explicit trigger condition — use it when a data tool returned with a still-'running' status — and a clear negative boundary: it does not start a new run. It stops short of naming the sibling tools that would start a run or giving polling cadence, but the when/when-not framing is solid.

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