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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds the crucial scope limit: only the single edge is removed and both endpoint objects survive. That directly answers the main fear an agent has about a destructive op. It doesn't say what happens if the edge is absent (error vs no-op) or whether the delete is reversible.

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 dense, front-loaded sentence carves out the exact scope, followed by a short actionable tip. No filler, nothing repeated from the title or schema.

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 3-param destructive edge deletion with full schema coverage and no output schema, this covers nearly everything. The remaining gap is failure behavior, whether a missing edge throws or is silently ignored, which matters when retrying a destructive call.

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 100%, so all three params are already documented, and the description reinforces the directional semantics with the from -> to arrow notation, tying from_object_id and to_object_id together as edge endpoints. The gain over the schema is modest but real, and it clarifies that connection_type names the relationship rather than a generic type.

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 description states a specific verb (Delete) and a precisely scoped resource (one connection/edge between two graph objects), not the objects themselves. The framing "the edge from_object_id -> to_object_id of the given connection_type, nothing else; both objects stay" cleanly separates it from the siblings connect_graph_objects and delete_graph_object.

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 explicit prep guidance: call get_graph_object first to learn an object's connections, their types, and their directions. That is a real prerequisite an agent would otherwise skip. It stops short of stating when not to use this tool (e.g. when you actually want to remove an object, use delete_graph_object), so it isn't a full routing guide.

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