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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint, openWorldHint), so the description's remaining burden is smaller. It does add real value the annotations cannot: the 10-credit Tier 1 cost and the claim that the draw is 'seeded like the fixed spreads,' implying reproducibility when a seed is supplied. However, it never states what happens when no seed is given (random draw?) or how allowReversed affects the outcome.

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 core sentence is front-loaded with the verb and carries the two-mode distinction with no wasted words. The three bracketed metadata lines are template boilerplate but the endpoint and cost lines carry actionable information; nothing is padded.

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 return values need no explanation, and the positions-vs-count duality is addressed. But with 8 all-optional parameters and no defaults described (allowReversed defaults true, seed absent means randomized), an agent still has to infer the draw's determinism model and the meaning of question from the schema alone.

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 coverage is only 63%, and the undocumented parameters are exactly seed, question, and allowReversed. The description restates the positions-vs-count choice and the 1-15 bound, both already in the schema, and 'seeded' is mentioned without explaining seed semantics (same seed = same draw, integer range). It does not compensate for the coverage gap.

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?

States a specific verb and resource (draw Lenormand cards) plus the defining trait of this variant: into positions you name or by count, 1-15. The 'custom' nature is implied and distinguishes it from fixed-spread siblings, but the description never names those siblings or says explicitly 'use this when no fixed spread fits.'

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?

'Into positions you name or by count' hints at the two input modes but is really parameter guidance, not when-to-use guidance. There is no statement of when to choose this over astroway_tarot_lenormand_draw_three_card or _grand_tableau, and no prerequisites or cost/benefit tradeoff guidance beyond the bare credit line.

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