load_graph

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

No annotations are provided, so the description carries the behavioral burden. It explains that the graph is loaded once and subsequent tools all operate on the in-memory copy, which is important state-changing behavior. It stops short of describing side effects like whether the old graph is discarded or if this can affect producers, but the core behavior is disclosed.

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?

The description is two dense sentences with no redundancy. The primary function is stated first, followed by the input shape and global side effect, which makes it easy to scan and reason about.

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?

Given that there is no output schema, this description covers the essential context: what the tool does, the provided inputs, and the side effect. It is somewhat sparse on error conditions or preconditions, but it is complete enough for selecting the tool in a normal workflow.

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?

The schema offers no description of the parameters, so the description must compensate. The description adds useful meaning: the path is a canonical graph JSON path, and overlay + profile are optional. Still, overlay and profile semantics are not fully explained, so an agent has to guess their purpose or consult external knowledge.

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 names a specific verb and resource relation: switch/attach the active graph the server reasons over, with an example of retargeting to a different graph. It clearly differentiates itself from loading/creating a new graph because it describes a session-wide swap of the in-memory active graph, which also distances it from the build_graph sibling.

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 concrete operational context: use this to change the active graph mid-session without restarting, e.g. from bnxt to igb. It does not explicitly say when not to use it or name alternative tools, but the scenario is clear enough for an agent to decide it is the tool for switch/attach operations.

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