Tarot Yes No

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

The annotations provide readOnlyHint=true, idempotentHint=false, and destructiveHint=false, and the description does not contradict these or claim any side effects. The description does not add extra context about safety, auth, or rate limits, but given the annotations already cover the core behavioral aspects, the description is sufficient and transparent.

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 with clear sections (WORKFLOW, INPUT CONTRACT, DO NOT CONFUSE WITH) but contains some redundancy, as the INPUT CONTRACT repeats parameter details already present in the schema. However, it remains concise overall and does not include extraneous information, making it easy for an agent to parse the essential guidance.

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?

The description fully covers the tool's purpose, usage, and distinctiveness from siblings, and the schema provides parameter details and output format options. Although the description does not specify the exact structure of the 'markdown' vs 'json' response, the schema's response_format enum and the mention of 'confidence level' give sufficient context for an agent to understand the expected output. Overall, the tool is well-specified.

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 elaborates on both key parameters: allow_reversed is explained in the INPUT CONTRACT with the note that setting it to false ensures strictly yes/no answers without 'maybe' from reversal, and question includes an example ('Should I accept this job offer?'). Combined with 100% schema coverage for all three parameters (including response_format), the semantic meaning of each parameter is fully conveyed.

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 states the tool 'Draws one card and returns a yes, no, or maybe answer with confidence level' and explicitly distinguishes it from siblings in the 'DO NOT CONFUSE WITH' section, noting that the three-card spread is a positional reading (not binary) and draw_tarot_cards is a free draw without answer logic. This fully clarifies the tool's purpose and its unique role among the listed tools.

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 WORKFLOW section clearly indicates this tool is standalone ('BEFORE: None') and recommends following up with asterwise_get_tarot_three_card_spread when the answer is 'maybe' or more context is needed. The 'DO NOT CONFUSE WITH' section additionally tells the agent when not to use this tool, providing clear usage guidance relative to alternatives.

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