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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries the behavioral load and does so well: it discloses that each call appends a fresh position row and preserves prior positions on the log (a key non-destructive mutation trait), and that the move fires the node's on_enter enactment on the next run with concrete consequences per node kind. It stops short of stating auth/credit requirements, but is otherwise rich.

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?

Front-loads the core purpose and is structured with summary/returns blocks, but the middle is dense with stacked em-dash parentheticals and repeated node-kind enumerations (once in the purpose, again in the enactment sentence) that partially duplicate each other. Efficient enough, but not maximally tight.

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 4-param mutation tool with no output schema but an inline returns block, the description covers routing intent, side-effect behavior, idempotency-like re-route semantics, and the enactment consequence. An agent has everything needed to call it correctly without further context.

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%, so all four parameters are already documented in the schema, including node_id's kind list and on_behalf_of's agency-client semantics. The description adds no additional parameter syntax or format detail beyond what the schema provides, so the baseline of 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 (move) and resource (prospect onto a flow node) and explicitly carves out the subset of moves it handles — those the automatic position writes can't place. It names the sibling concept (automatic paths) so an agent can distinguish this tool from the flow-definition tools like update_node and get_campaign_flow.

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 both when-to-use (decision-arm move and `then` target the automatic paths don't cover) and an explicit when-not / do-not ('do not compose the send here'), plus the re-route case (calling again corrects or re-routes). Nothing is left to inference about intent.

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