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

With no annotations, the description carries the whole burden and does so: it warns that a RUNNING run is partial, that initialData values are shortened with initialDataTruncated listing cut paths, that block names/types are absent when the configuration is gone, that failure is only populated for TERMINATED runs, and that olderRunsHiddenByPlan replaces the entire result. It also gives the precise semantics of configChangedSinceRun, including the caveat about edits made after stopping that were not restarted.

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 purpose is front-loaded and almost every clause carries real information, but the result is one dense run-on paragraph with stacked parentheses and semicolons that is hard to scan. Since no output schema exists the length is defensible, yet it could be split into field-oriented sentences without losing content.

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 and no annotations, so the description must define the return shape and its edge cases — it enumerates every result field (executionId, versionId, configId, status, terminationReason, timestamps, durationMs, initiator, failure, steps, notExecuted) and explains the degradation cases. That is complete enough for an agent to interpret the response 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?

Schema coverage is 0%, so the description must supply meaning: it explains that instanceKey is derived from list_flow_instances and defines both include values (initialData and pendingOn, including '[] when it waits on nothing') plus the lazily-fetched behavior ('each is fetched only when listed'). workspaceId is never mentioned, leaving one of three parameters undocumented.

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 first clause, 'Overview of one run', names the resource (a single flow instance/run) and the operation, and immediately distinguishes it from list_flow_instances by stating where instanceKey comes from. It also separates itself from get_flow_instance_block, so an agent can tell the three siblings apart without opening a schema.

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?

It routes the agent explicitly: instanceKey comes from list_flow_instances, block input/output requires get_flow_instance_block, and configId with versionId should be passed to get_flow_summary / get_node_details / get_flow_json to see the flow as it was at run time. It never states when *not* to use this tool (e.g. use list_flow_instances for discovery), which keeps it short of a full 5.

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