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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description is consistent with them (no contradiction). Beyond annotations, it discloses valuable behavioral traits: bidirectional edge traversal, shortest-path guarantee, the specific edge kinds included (FK, DeleteAction, DataSource, Extension, Security), token-light output that never returns full object source, and O(1)-per-node BFS cost. This materially helps an agent reason about cost and output size before invoking.

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?

Well front-loaded with the WHEN clause, and every sentence earns its place: triggers, mechanism, output format, token-light note, complexity, and sibling routing. It is slightly long due to the trigger-phrase list, but that list directly aids an agent's selection matching, so the length is justified.

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?

With no output schema, the description properly conveys the return shape ('chain of object names + edge kinds'), and annotations cover the safety profile. It is missing edge-case behavior for what happens when no path exists within maxDepth or when source/target are identical or unreachable, but this is a minor gap against an otherwise rich definition.

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 the schema already fully documents source, target, maxDepth, and maxPaths with defaults and bounds. The description adds only loose context ('multiple hops', 'SHORTEST path'), not operational detail beyond the schema. Baseline 3 is appropriate.

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+resource combination ('Walks the pre-computed relation graph... returns the SHORTEST navigation path(s)'), which is far more precise than the name alone. It explicitly differentiates from the sibling get_relation_graph: full neighbourhood of one object vs. multi-hop traversal between two known objects.

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?

Opens with a WHEN clause stating the exact condition ('you need to know HOW two AOT objects are connected') and gives concrete trigger phrases in two languages. It also names the alternative explicitly ('Use get_relation_graph for the full neighbourhood of a single object; use this to traverse multiple hops between two known objects'), leaving no selection ambiguity.

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