Forged in the Dark

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

The description discloses the mutating sub-operations (mark/clear/resist stress, recover/indulge vice) and the random/deterministic nature of action rolls via dice and seed, which goes beyond the minimal readOnlyHint/openWorldHint annotations. It does not contradict the annotations, though it could state persistence or side effects more explicitly.

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 short and front-loaded: a one-sentence purpose, followed by crisp use/no-use guidance. Every sentence adds information, and the formatting makes the selection criteria easy to scan.

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 tool with no output schema, the description provides enough operational context to choose and invoke the correct sub-operation, including defaults and exclusions. It does not describe output shapes, but that is less critical given the explicit schema and the simple sub-operation model.

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 descriptions already cover all 10 parameters with defaults and enums, so the description adds little beyond grouping them into sub-operations. It reinforces the role of cost, dice, position, and effect, but does not substantially extend the schema's meaning.

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 ('Resolve') and names the exact domain (Blades in the Dark-style actions), then enumerates the three supported areas: action rolls, stress/resistance, and downtime recovery. It also distinguishes itself from countdown tracking, leaving no ambiguity about what the tool does.

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 provides explicit 'Use when' conditions for each supported kind of roll and a 'Do NOT use when' rule that routes progress-clock tracking to the countdown tool. This gives an agent clear selection criteria and an explicit alternative.

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