Create Flow Version

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

Annotations only declare destructiveHint=false; the description adds the genuinely useful behavior that this is a non-destructive safeguard and that update_flow is irreversible without it, which is exactly the risk context the annotation does not convey. It does not say whether snapshots are capped, versioned automatically, or returned in the response, but the core safety profile is well covered.

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?

Two sentences, zero filler, and the imperative action plus motivation are front-loaded before the cautionary clause. Every sentence earns its place.

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 low-complexity two-parameter create tool with no output schema, the description supplies purpose, trigger condition, and the consequence of skipping it. The only gap is that it never indicates what the call yields (a version identifier usable with restore_flow_version), which would help an agent chain calls.

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% (both id and label are documented, including a label example), so the baseline is 3. The description adds no parameter-level guidance of its own, such as recommending a descriptive label for later identification, so it neither compensates nor detracts.

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 — 'Snapshot the current state of a flow' — plus the purpose (restorable later). It also names the sibling it complements (update_flow), so an agent can place it among create_flow/update_flow/list_flow_versions/restore_flow_version without opening schemas.

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 triggering condition: take a snapshot before rewriting a flow you did not build, and explains why (update_flow replaces the descriptor, no undo). It stops short of routing to the counterpart tools — restore_flow_version for reverting and list_flow_versions for enumerating existing snapshots — so the lifecycle guidance is clear but incomplete.

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