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

With no annotations, the description must carry behavioral disclosure. It does reveal a key constraint (max 12 parts per call) and a concurrency rule (wait between calls). It does not disclose validation behavior, duplicate handling, or what happens on invalid input, which would matter for a mutation tool.

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 short sentences with no filler. It front-loads the core action and limit, then delivers the call-pattern and input-format guidance. Every clause adds usable information.

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 core purpose and part schema are well covered, but the description lacks lifecycle context: it does not mention that forge_handle must be obtained via enter_forge, nor what the response tells the agent. For a complex tool with no output schema and no annotations, some of that context would be valuable.

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 only 50%, but the description adds meaningful parameter semantics: it states the acceptable count range and clarifies that parts may be supplied as a JSON list or a stringified list. This goes beyond the raw schema types. It does not repeat the detailed nested part schema, which is already well documented.

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 ('Add') and resource ('parts') with a concrete quantity range ('1 to 12 parts'). The sibling names (forge_edit, forge_remove, forge_keyframe, forge_observe) make the distinct action clear; an agent can tell this tool creates new parts rather than modifying or removing them.

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 gives practical invocation guidance: send one call, wait for the answer before the next, and pass parts as a JSON list or string. However, it does not explicitly contrast this with alternatives such as forge_edit or forge_remove, nor does it state when not to use this tool.

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