dbt-graph

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

No annotations are present, so the description carries the full burden. It discloses the traversal mechanism (parent_map/child_map) and depth constraint but omits side effects, cost considerations, or read-only nature. For a tool with no annotations, more behavioral context is needed.

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 a single, well-structured sentence that immediately states the action and output. No extraneous words; every phrase 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?

Given no output schema and moderate parameter count, the description covers the basic action and output type (nodes) but lacks details on return format, prerequisites (e.g., dbt manifest), or behavior for invalid inputs. It is adequate but not thorough.

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 documentation covers 50% of parameters (uniqueId, name). The description adds 'up to a given depth' but does not clarify semantics for depths (e.g., what depth 0 means) or how name resolves when uniqueId is absent. The description fails to compensate for the incomplete schema coverage.

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 clearly states the tool walks dbt parent_map/child_map to return upstream and downstream nodes, which is a specific action on a resource. It distinguishes from sibling tools like dbt-get-model (single node retrieval) by focusing on lineage traversal.

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 does not provide explicit guidance on when to use this tool versus alternatives like dbt-get-model or dbt-list-models. The purpose implies lineage exploration, but no when-to-use or when-not-to-use context is given.

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