save_check

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses the caller-rolls-d20 contract, return object shapes for both modes, condition auto-fail/disadvantage rules, exhaustion penalty, and error behaviors (missing-fact, structured recovery classes). This goes well beyond minimal expectations.

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 earns its place. It front-loads the core purpose, then efficiently covers optional condition handling, return modes, and error cases without redundancy or fluff.

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?

While the description is thorough for the basic saving-throw adjudication workflow, it omits the substantial policy/table/asserted-facts machinery that the schema exposes. Given the nested objects and output schema, an agent would be underprepared to use those advanced parameters 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 description adds useful context for save_ability, saver_conditions, d20_result, and exhaustion_level beyond the schema. However, it completely ignores several complex parameters (table_policy, asserted_facts, policy_context, table_decision) that have no schema descriptions, and with 55% coverage, the description does not fully compensate for those gaps.

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 uses a specific verb ('Adjudicate') and a specific resource ('a saving throw against a DC') with an SRD citation, making the tool's purpose immediately clear. It distinguishes itself from sibling tools like check_make and concentration_check by focusing on saving throws and DC resolution.

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 clearly explains two invocation modes (with d20_result vs. without) and explicitly states when to pass save_ability + saver_conditions for condition-aware overrides. It does not explicitly name alternative tools or state when NOT to use this tool, but the purpose clarity largely handles differentiation.

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