Lineage

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

Annotations already declare read-only/open-world safety, and the description adds genuinely new behavioral detail: a hard 10-step traversal cap, which edge types are followed, which are not (containment), and the resulting edge case for single fields. It also sketches the return payload (anchor, nodes, edges with source_id -> target_id and type, counts), which goes beyond what the annotations convey.

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-loaded with the core purpose, then edge-type scope, then containment caveat, then return shape and alternative. Every sentence adds information; the example ('a data source and the workbooks built on it') and the two quoted questions efficiently anchor usage.

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?

Output schema exists, so return values need not be fully explained, and the description still summarizes them. Traversal semantics, limits, and alternatives are all covered. The main gap is the undocumented `graph_id` parameter and whether it scopes the traversal to a particular graph.

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 0%, so the description carries the burden. It clarifies that `node` accepts either a node id or a plain-language description, which is valuable, but the second parameter `graph_id` (nullable, default null) is never mentioned, leaving half the parameters undocumented.

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 resource and traversal scope ('lineage neighborhood of a node: every node reachable within 10 steps, upstream AND downstream, along lineage/dependency edges') and names the edge types followed. This is clearly distinguishable from siblings like impact_analysis, list_edges, and get_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?

Explicitly names the questions it answers ('where does this come from?', 'what uses it?'), states the exclusion (containment edges not followed, with the consequence that a single field returns only itself), and redirects to list_edges/get_node for containment and to impact_analysis for 'what breaks if this changes?'.

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