invariance_run_fork

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

The description states that the tool creates a new run that 'branches off' the parent, which is meaningful behavioral disclosure beyond the annotations. It is consistent with readOnlyHint=false and destructiveHint=false. It could add more detail about whether the parent run is modified or whether the fork is immediately executable, but the core side effect is clearly communicated.

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 description is compact: two sentences, front-loaded with the operation, followed by a practical use case. Every phrase earns its place, with no fluff or repetition of the schema.

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 moderate-complexity tool with a clear schema and annotations, the description covers the essential purpose, mechanism, and use case. It is slightly incomplete in that it doesn't describe the return value or explicitly contrast with run-start tools, but nothing critical is missing for correct invocation.

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?

The schema already documents id, from_node_id, and metadata, providing 75% coverage. The description reinforces the role of from_node_id through 'branches off the parent at from_node_id' but does not add new semantics for name or metadata. This is adequate but not additive beyond what the schema already provides.

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 ('Fork') and a concrete resource ('a run'), and explains the core mechanism: branching off the parent run at from_node_id. This clearly distinguishes it from sibling tools like invariance_run_start or invariance_create_run, which imply fresh run creation rather than forking an existing run at a node.

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 names an explicit use case: 'what-if replays during agent debugging.' This gives the agent clear context for when the tool is appropriate. However, it does not explicitly name alternatives or state when NOT to use it, such as when a fresh run is needed instead of a fork.

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