Record Goal Interpretation

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

The description discloses that the tool overwrites existing interpretations (not idempotent), raises an error if called at the wrong time, and returns the full updated Goal card dict. These details go beyond the annotations (readOnlyHint false, destructiveHint false) and provide important behavioral context.

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 well-structured and concise, with each sentence serving a purpose. It avoids fluff and presents information logically: purpose, timing, parameter details, error conditions, and return value. The repetition of key points is minimal and does not detract from clarity.

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 sparse schema (only a string parameter with no description) and no output schema, this description provides complete context: what the tool does, when to call it, what the parameter means, what errors can occur, and what it returns. It also relates to other tools (draw_goal_card, complete_goal, get_sheet), making it self-contained.

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 thoroughly explains the 'interpretation' parameter: it should be a plain-language sentence or two capturing what the Goal means, and explicitly states it should not be a verbatim quote. This adds significant meaning beyond the schema's simple string type.

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's purpose: to save the player-and-Claude-agreed meaning of the Goal card. It distinguishes itself from siblings by explaining its role in the flow (e.g., it feeds into complete_goal) and provides specific context about when it is used.

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 explicitly states when to call: once, during the Sitting, right after the player has answered and Claude has reflected. It also notes a precondition (must be after draw_goal_card) and an error condition (raises ValueError if called too early), giving clear usage boundaries.

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