mage_hand_use

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

With no annotations, the description carries full behavioral disclosure. It reveals conditional fact-request behavior (distance for granted uses, weight for carrying/manipulating), states that prohibitions won't request irrelevant facts, and explains the fallback behavior for out-of-list uses (cannot-adjudicate with gm-discretion and resolve-table-ruling). This is unusually transparent.

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 dense but every clause adds value: purpose, allowed/prohibited categories, limits, fact requirements, conditional behavior, and fallback. It front-loads the verb and resource, avoids fluff, and is appropriately sized given the tool's complexity.

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?

Despite good core guidance, the description omits critical information about the complex nested parameters. It mentions 'resolve-table-ruling' and 'agent-DM may rule directly,' but does not explain how to populate table_policy or table_decision, nor the role of asserted_facts and policy_context. Without this, an agent cannot confidently invoke the tool for out-of-list or DM-ruling scenarios. An output schema exists but is not shown, so the description should have covered these gaps more explicitly.

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 13%, so the description must compensate. It does for the core parameters: kind (via the granted/prohibited lists), distance_ft, and weight_lb (via the fact-requirement rules). However, it gives no semantic guidance for complex parameters like table_policy, asserted_facts, table_decision, or policy_context, leaving their roles unclear.

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 opens with a specific verb and resource: 'Adjudicate one proposed use of the Mage Hand cantrip,' and enumerates the exact use categories, carry limit, and range. This clearly distinguishes it from generic tools like table_evaluation or spell_facts, though it does not explicitly name sibling tools or contrast itself with 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 specifies exactly when to use the tool (for any proposed Mage Hand use) and when not to (uses outside the can/can't lists). It also provides an explicit alternative: 'an authorized agent-DM may rule directly,' satisfying the when/when-not/alternatives criterion.

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