armorpaint_get_material_graph

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the 'Read' verb aligns with them - no contradiction. Beyond the annotations, the description discloses what the graph comprises (socket values, buttons, connections, not just nodes) and the default behavior that material_id=-1 resolves to the current material, which annotations do not convey.

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?

Two sentences, both high-value: the first states the operation and its exact scope; the second explains the sentinel parameter. No filler words, front-loaded with the purpose. Every sentence earns its place.

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?

An output schema exists to document return shape, and annotations cover the safety profile, so the description only needs to carry operational context, which it does. The only gaps are edge cases: behavior for invalid material_id values and whether an empty/fresh material returns an empty graph. These are minor for a simple single-parameter read tool.

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 0%, and the schema offers only type, default, and minimum. The description supplies the critical semantics - material_id=-1 means the current material - which is essential for correct invocation. It leaves some ambiguity about what non-default integer values reference (an index, a generated ID, or an app-assigned material name) and what happens for out-of-range IDs, but the key behavior is explained.

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 and resource: 'Read a material's nodes, socket values, buttons, and connections.' The read scope clearly sets it apart from mutating siblings like armorpaint_set_node_value, armorpaint_connect_nodes, and armorpaint_add_node, and from the more genera armorpaint_get_state. Even the closer sibling armorpaint_list_node_types is distinguishable - that tool lists node types, this one reads a specific material's graph.

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?

Context is implied: you would call this when you need to inspect a material's node graph, and the sentinel hint tells you how to target the current material. However, there is no explicit when-to-use versus alternative tools, no exclusions, and no mention of a prerequisite such as selecting a material first.

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