Draw Tarot Cards

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description is consistent with them. It adds significant context beyond annotations: cryptographic randomness via Python secrets.SystemRandom, per-call independence with no session state, local rejection of out-of-range counts with MCP INVALID_PARAMS, and a 50% per-card reversal chance that is explicitly 'not seeded.'

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 front-loaded with the core behavior in the first sentence, then organized into labeled sections (WORKFLOW, INPUT CONTRACT, DO NOT CONFUSE WITH) that make it scannable. There is no filler; examples, validation notes, and the docs link all earn their place, and the length is proportionate to the three near-sibling tools it must disambiguate.

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?

Between the annotations (safe read operation), the output schema, and the docs link for the full output/error contract, nothing an agent needs to invoke this tool correctly is missing. The reminder to interpret drawn cards via active_meaning and active_keywords fields also closes the loop on how results should be consumed.

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?

With 100% schema description coverage, the schema already documents all three parameters; the description adds strong value with concrete examples (1 daily pull, 3 simple reading, 10 Celtic Cross, 78 full deck), the 1–78 boundary with local validation behavior, and probability mechanics for allow_reversed (50% per card, independent, not seeded). Minor gap: response_format is absent from the INPUT CONTRACT section, though its schema description is thorough.

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 and resource — 'Draws N unique random cards from the 78-card deck' — and adds scope-defining traits (unique, cryptographic randomness, no session state). The 'DO NOT CONFUSE WITH' block names the three closest tarot siblings and their distinguishing behavior, so an agent can select this tool without opening their schemas.

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?

Explicitly states the tool is standalone with no prerequisites or follow-up ('BEFORE: None', 'AFTER: None'). The 'DO NOT CONFUSE WITH' section names asterwise_get_tarot_card_of_the_day, asterwise_get_tarot_three_card_spread, and asterwise_get_tarot_celtic_cross with the precise differences (deterministic vs positional vs random), leaving no ambiguity about when this tool is the right choice.

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