request_chapel_key

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

With no annotations, the description carries full behavioral transparency burden. It discloses prerequisites (killing what came through), inputs (answer and sincerity), consequences (key granted only for honest/uncertain), and long-term effects (Bren remembers verbatim forever). No contradictions with annotations (none exist).

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 relatively long but well-structured: condition, roleplay instruction, input explanation, outcome rules, final admonition. Every sentence adds necessary context. Slightly verbose but efficient for the complexity; loses one point for not being as terse as possible.

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 narrative complexity and lack of annotations/output schema, the description covers all needed context: prerequisites, inputs, process, outcomes, and agent role. It is fully complete for correct invocation.

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 has 0% description coverage, so description must add meaning. It clearly defines 'answer' as the player's response to Bren's question, and 'sincerity' with explicit valid values ('honest | uncertain | selfish | flippant') and their outcomes. This fully compensates for missing schema descriptions.

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 handles a specific narrative event: requesting the chapel key on Day 1 after a prerequisite action. It uses specific verbs ('request', 'roleplay', 'pass', 'judge') and distinguishes from sibling tools like 'talk_to' or 'advance_loop' by its conditional and judgment-based nature.

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 provides explicit when-to-use conditions ('Day 1 only, at the chapel, AFTER...'), step-by-step instructions ('Roleplay Bren's question first... then pass the player's actual answer...'), outcome rules based on sincerity values, and a final directive ('Judge fairly — this is the one place your judgment is the rule'). It covers usage context comprehensively.

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