turn_plan

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

With no annotations, the description fully discloses behavior: it returns legal/illegal/cannot-adjudicate with citations, and illegal verdicts name the first offending step. It also explains error handling ('Unmodeled conditions and out-of-range inputs return exit 2 rather than a guess') and the exact scope boundaries, making the tool's behavior highly predictable.

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 concise at roughly 90 words and front-loaded: the first sentence states the purpose and core rules, the second explains output, and subsequent sentences handle scope and error behavior. Every sentence adds unique information without redundancy.

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 (10 parameters, nested objects) and the presence of an output schema, the description adequately covers the core adjudication logic and error modes. It omits guidance on how the policy/table context parameters (table_policy, asserted_facts, table_decision) interact with the judgment, but these may be shared infrastructure. The explicit scope and error handling make it sufficiently complete for an agent to select and invoke the tool for its primary purpose.

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 50%, leaving many parameters (table_policy, asserted_facts, policy_context, table_decision) undocumented in both schema and description. The description does add some validation semantics not in the schema, such as rejecting 'negative speed' and 'spell level >9,' and references movement edge cases (crawling, standing from Prone, Grappled speed 0) that clarify plan step semantics. However, it does not compensate for the large set of unexplained auxiliary parameters, so it meets the baseline but doesn't exceed it.

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 'Judge' and a precise resource: 'a whole proposed turn under SRD 5.2.1 ACTION ECONOMY.' It enumerates the exact rules covered (action/bonus-action/reaction/free-interaction budgets, movement, Incapacitated, one-spell-slot rule) and explicitly distinguishes itself by stating it does NOT verify feature-granted actions, which differentiates it from siblings like attack_modifiers or turn_options.

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 delineates when this tool is appropriate ('this checks the turn's economy only') and what it does not cover ('does NOT verify that a feature grants a given action'), which implies when to look elsewhere. It also notes out-of-range inputs return exit 2, signaling a boundary condition. However, it does not explicitly name alternative sibling tools or give a positive 'use this if...' statement.

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