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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and scope are covered structurally. The description adds one genuinely useful behavioral fact — links are 'directly' connected, i.e. a single hop, not transitive closure — and that link kind is included. It says nothing about direction, pagination, or volume of neighbors.

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?

One tight sentence with the key qualifier ('directly linked') front and center, and the return-content hint ('kind of each link') at the end. No filler, though it could be front-loaded with a verb for scanability.

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 traversal tool with zero-annotated parameters and no output schema, the description leaves out link direction (incoming vs outgoing vs both), how many neighbors may come back, and the shape of the relationship records. It states the concept but not enough for an agent to predict results or handle edge cases.

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 0%: both campaignId and entityId are bare strings with no descriptions. The description only weakly implies that entityId identifies the anchor entity and campaignId scopes the graph; it adds no format, ID convention, or behavior for missing/invalid IDs.

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?

Names the resource precisely: entities directly linked to one entity in the campaign graph, plus the link kind. This distinguishes it from sibling reads like get_entity (single entity) and list_entities (all entities), though it is a noun phrase with no explicit verb.

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?

No when-to-use guidance and no mention of alternatives such as get_entity, list_entities, or search_entities. The agent must infer from the name and phrasing that this is the traversal/adjacency lookup, with no stated exclusions or prerequisites.

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