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

Annotations already declare this as a non-readonly, non-idempotent, non-destructive, open-world mutation. The description adds substantial extra context: that it makes no AI call, reads the dbt Discovery API applied state or a job manifest, defines the exact node/step/system/edge mapping rules, states the 250-node limit, and explains default environment selection.

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?

It is front-loaded with the core action and remains dense with useful detail across a few well-organized sentences. Every sentence earns its place given the nine parameters and complex mapping behavior; there is no filler or repetition.

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 complex, nine-parameter write tool with no output schema, the description is complete enough: it explains creation behavior, list_only output, selection defaults, environment fallback, node limits, and what the resulting flow contains. Safety-relevant traits are already covered by annotations.

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 100%, so the schema already documents each parameter. The description adds meaningful interaction semantics beyond the schema: select maps upstream lineage, downstream true extends to downstream dependencies, omitting select maps the whole project under a node cap, omitting both environment_id and job_id picks the first deployment environment, and list_only changes output from a flow to a list.

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 sentence states a specific verb and resource: mapping dbt lineage into a new Wavelength flow, with the distinctive note 'no AI call.' It then details exactly what becomes data nodes, steps, systems, and edges, distinguishing it from generic flow-creation or other lineage imports.

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 clearly explains how to use key parameters: select for upstream lineage, downstream to extend it, no select for whole-project (if ≤250 nodes), and no environment_id/job_id for the first deployment environment. However, it never names sibling alternatives like import_snowflake_lineage or create_flow_from_graph to tell the agent when to select this tool over them.

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