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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered. The description adds genuinely new context: the all-or-nothing atomicity, that no generation is triggered, and that the response maps localId to node id. It does not cover permission needs or revision-conflict behavior.

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?

Four tightly packed sentences, front-loaded with the core operation and followed by the exact referencing mechanics an agent needs. No filler or repetition of the name.

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 9-parameter mutation tool with no output schema, the description covers the essential mechanics: atomicity, localId resolution, and the response mapping. It omits revision-conflict handling and the meaning of expectedRevision, but the schema supplies that for the required parameter.

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 description coverage is only 22%, so the description has to compensate, and it does for the hardest parts: it defines localId, states that connections carry only from/to/targetHandle, and explains placements reference localIds. It leaves other parameters (updateNodes, deleteNodeIds, addFileNodes) to 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?

States a specific verb set (add, update, connect, place, delete) over concrete resources (nodes and edges), and names the transaction model (one all-or-nothing edit). An agent can tell this apart from run_node because the description explicitly says it never starts generation.

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?

Provides the key usage rule that this is a pure edit operation ('Never starts generation'), which routes the agent away from run_node. It also explains how newly added nodes are referenced (localId) in the same request. It does not name alternative tools explicitly, so it falls short of a full when/when-not framing.

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