Generate class parameter curve

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

With no annotations provided, the description carries the safety burden well: it discloses that classId causes a write, that only minLevel..maxLevel rows change while 'other levels are untouched', and that dryRun defaults to true. It stops short of stating reversibility or whether a changeset must be open (siblings begin_changeset/commit_changeset imply that may matter), leaving one real gap.

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?

Four tight sentences, front-loaded with purpose, then the shape vocabulary, then the preview/write fork and the dry-run default. Every clause earns its place; nothing is repeated from the schema.

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?

For a five-parameter mutation tool with no annotations and no output schema, the description covers the essential decision points: preview vs apply, level range scope, and the follow-up tool. The remaining omission is workflow integration (changeset/commit requirements for the write path), which would matter for an agent editing a live project.

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 20%, so the description has to compensate, and it does: start/end endpoint meaning, the classId write target, and dryRun semantics are all clarified, plus the shape names are explained in plain terms ('ease-in (slow start)', 'exponential (constant growth factor)') beyond the bare enum. It does not convey minLevel/maxLevel defaults or the 8-item cap on curves, but the core meaning is supplied.

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+resource ('Generate stat curves over levels') and immediately distinguishes the two operating modes: pure preview without classId vs. rewriting the class params table with it. Its curve-shape vocabulary and level-scoping language make it clearly separable from siblings like generate_enemy_scaling and balance_report.

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?

It names the exact condition that switches behavior ('Without classId ... With classId ...'), specifies the dry-run default and how to override it (dryRun=false), and hands off the natural follow-up ('Follow up with balance_report'). An agent has no ambiguity about when to call this or what comes next.

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