attempt_arcane_synthesis

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly explains the tool's behavior: DC calculation with modifiers, outcomes (Mastery, Success, Fizzle, Backfire, Catastrophic), and damage guidelines. This includes risk factors (e.g., mishaps, damage to caster, WILD SURGE), which are critical for an AI agent to understand the consequences of invoking this 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 appropriately sized and well-structured, with sections for DC Calculation, Modifiers, Outcomes, and Damage Guidelines, followed by an example. Each sentence adds value, such as explaining mechanics and risks. However, it is somewhat lengthy due to the complexity of the tool, which is justified but slightly reduces conciseness.

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?

Given the tool's high complexity (17 parameters, nested objects, no output schema, no annotations), the description is complete enough. It covers purpose, usage context, behavioral details (including risks and outcomes), parameter semantics, and provides an example. This compensates for the lack of structured fields, ensuring an AI agent can understand and invoke the tool correctly.

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?

The schema description coverage is low (18%), so the description must compensate. It adds significant meaning beyond the schema by explaining how parameters affect outcomes: e.g., 'encounter_id' adds +2 DC if in combat, 'estimated_level' influences base DC and damage, and 'circumstance_modifiers' map to specific DC adjustments. The example illustrates parameter usage in context, clarifying semantics that the schema alone does not provide.

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 tool's purpose: 'Attempt to create a spell on the fly through Arcane Synthesis.' It specifies the action ('create a spell') and the mechanism ('Arcane Synthesis'), distinguishing it from sibling tools like 'create_spell_scroll' or 'use_spell_scroll' which handle predefined spells. The detailed mechanics further clarify this is for improvisational spell creation.

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 clear context for when to use this tool: for creating spells dynamically based on narrative intent and specifications. It implicitly suggests usage when a player wants a custom spell effect not covered by existing spells. However, it does not explicitly state when not to use it or name alternatives (e.g., 'use_spell_scroll' for predefined spells), which prevents a perfect score.

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