Impact analysis

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

Annotations already declare readOnly/openWorld/non-destructive, so the bar is lower, and the description adds real value beyond them: traversal edge type (DEPENDS_ON), a depth cap of 10 steps, and the fact that the queried node is excluded from results. It does not say what happens when the depth cap truncates a larger blast radius, which is the one behavioral detail an agent would want.

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?

Three short blocks: the purpose/scope lead, the input note, then the return keys. Every sentence carries information (scope, depth limit, edge type, self-exclusion, return shape) with no filler, and the highest-value content is front-loaded.

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?

An output schema exists, so the brief mention of `total`, `counts_by_type`, and sorted `affected_assets` is sufficient rather than redundant. For a two-parameter read tool with annotations, the only real omission is the undefined `graph_id` and truncation behavior at the 10-step limit.

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 must carry parameter meaning. It does well for `node` (accepts a node id OR a plain-language description, a non-obvious flexibility), but `graph_id` is never mentioned at all, leaving the second parameter entirely unexplained.

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?

Opens with a concrete verb-in-context question ('What breaks if this changes') and precisely defines the resource: every asset depending on the node, direct or transitive, up to 10 steps along DEPENDS_ON. The examples (calcs, sheets, dashboards, workbooks downstream of a column) and the explicit exclusion of the node itself leave no ambiguity about what the tool returns versus a generic 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 'what breaks if this changes' framing gives a clear use context, and the DEPENDS_ON/10-step scope implies when a broader traversal (e.g. the `lineage` sibling) would be the alternative. However, it never names an alternative or states a when-not-to-use condition, so the agent must infer the boundary with `lineage` itself.

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