encounter_xp_budget

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

No annotations are provided, so the description carries the transparency burden. It discloses the return behavior (per-character XP budget with citation) and the total when party_size is passed, implying a read-only calculation. However, it does not discuss edge cases (e.g., invalid level/difficulty), state whether any state changes occur, or clarify any rate limits or authorization needs. This is adequate but not comprehensive.

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 two sentences long, with the first sentence front-loading purpose and primary inputs/outputs, and the second providing usage guidance. There is no filler or repetition of schema details; every clause adds useful information.

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?

An output schema exists, so the description need not detail return fields. It provides the essential workflow hint (combine with creature.stats) and mentions the citation. However, given the schema's complexity (nested policy objects, many optional parameters), the description does not address how the total is represented when party_size is provided or how to interpret the difficulty values beyond the basic enum. It is complete for the primary use case but leaves some integration details to the schema.

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 only 13%, so the description must add meaning to parameters. It maps 'level' to party level, 'difficulty' to low/moderate/high, and clarifies that 'party_size' yields the total budget, adding value beyond the raw schema. The remaining parameters (request_id, table_policy, etc.) are likely generic infrastructure fields and not explained, but the description compensates for the core domain parameters.

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 clearly states the tool provides 'XP budget per character for encounter building' and specifies the key inputs (level, difficulty) and output (per-character budget with citation). This distinguishes it from sibling tools focused on combat mechanics like attack_modifiers or check_make. The resource and action are explicit and unambiguous.

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 says the tool is for 'encounter building' and gives concrete combination guidance: 'Combine with creature.stats to check whether an encounter is within budget.' It also explains the optional party_size behavior and how to get a total. However, it does not explicitly state when not to use this tool or mention alternative budget methods, so it stops short of a 5.

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