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

Beyond the minimal readOnlyHint:false annotation, it discloses critical behavior: edges are directed, duplicate connections are idempotent (no-op rather than error), and the 'introduced' edge must use the exact spelling to be discoverable. This goes well beyond the structured fields and helps the agent anticipate side effects.

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 front-loaded with the core operation and examples, then provides the no-op behavior and the special-case rule. It is slightly verbose in the final sentence about 'the only spelling', but all content is relevant and there is no fluff.

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?

The description gives enough context to invoke the tool correctly: what the edge means, where IDs come from, idempotency, and the introduced special case. It doesn't mention return values or error behavior for invalid IDs, but for this operation the guidance is largely complete.

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?

Although the schema describes each parameter, the description adds semantic detail: object_ids should come from previous create/search/list calls, connection_type is generally free-choice but has one special exact value, and the from/to directionality is reinforced with examples. This meaningfully supplements 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 description clearly states the action: 'Connect two objects in the user's graph with a directed edge'. It names the resource (graph objects), the directionality, and gives concrete examples (file to project, person to event), which distinguishes it from node creation/deletion tools. The special 'introduced' case reinforces the specific purpose.

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?

The description provides concrete usage context: use object IDs returned by create/search/list, and it specifies exactly when to use the 'introduced' edge type. It does not explicitly name sibling alternatives like disconnect_graph_objects or create_graph_object, so exclusion guidance is implicit rather than explicit.

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