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 description does not contradict them. Beyond that, it richly discloses behavior: RECORD mode for class-less characters, warn-only prerequisites, delta counts in growth[], prerequisite-filtered choice pools, null spellSlots when fewer than two casters contribute, and the fact that vault_level_up_pc rejects class-less characters. This goes well beyond what annotations or the schema alone 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?

The description is long, but the length is justified by two modes, an edge case (no class entries), and important semantics like delta counts and prerequisite filtering. It is front-loaded with the core purpose and organized by mode. It loses a point because it partially restates details already present in the exhaustive schema, making it denser than strictly necessary.

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 complexity — three parameters, dynamic modes, sub-flows for class-less characters, and a rich output schema — the description is complete. It covers preconditions (record classes first), sequencing (read before vault_level_up_pc), postconditions (picks must come from returned options), and exceptional states (warn-only multiclass entry), so an agent has enough context to invoke it correctly in the broader level-up workflow.

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 100%, so the baseline is 3, but the description adds mode-level meaning to each parameter: no classRuleId yields the CHOOSER, classRuleId selects a held class or a multiclass candidate for the TARGET PLAN, and subclassRuleId previews a tentative pick before commitment. It also explains the relationship between classRuleId values and the chooser output, which the schema alone does not make explicit.

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 precise action ('Read the level-up plan for a 5e24 character') and names the exact resource and computation it mirrors. It distinguishes the tool's two modes (CHOOSER vs TARGET PLAN) and calls out related siblings like vault_level_up_pc and vault_record_pc_classes, so an agent can tell it apart without opening schemas.

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 explicit usage conditions: omit classRuleId for the chooser, supply it for a target plan, and add subclassRuleId to preview a subclass pick. It also prescribes the workflow — read before vault_level_up_pc, record classes first when class-less, and key picks off the returned data — which is actionable routing guidance beyond the schema.

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