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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds the pagination model (limit/cursor, page.nextCursor), the constraint that direction requires entity, and the shape of returned edges. These are genuine behavioral disclosures beyond the annotations, though the output schema already carries the return structure.

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 compact sentences, front-loaded with the resource and purpose before the parameter walkthrough. The parameter enumeration is dense but each clause carries distinct semantics; there is little filler.

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 read-only, six-parameter filtered list with an output schema, the description covers purpose, filtering semantics, the entity/direction dependency, and pagination. Since the output schema exists, the redundant return-value sentence is harmless rather than necessary, and no critical invocation detail is missing.

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 only 33% (entity, direction, via, type lack schema descriptions), so the description does real work: it defines entity as an id or address, constrains direction to out/in/both and notes it needs entity, and explains that type means the far end's type, or either end's when entity is absent. That conditional semantics meaningfully exceeds the schema.

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 opening sentence identifies the resource ('the model's edges') and its treatment ('filtered and paged'), and the second sentence clarifies the intent to inspect relations without pulling whole entities, implicitly contrasting with get_entity/list_entities. It never names the sibling tools directly, so differentiation is inferential rather than explicit, keeping it just below a 5.

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?

It gives a clear use case ('inspect one entity's relations or one kind of reference without taking whole entities'), which tells the agent when this is preferable to fetching full entities. There are no explicit exclusions against the other relation-oriented siblings (describe_relations, describe_schema), so it stops short of full routing guidance.

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