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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description does add real operational context the annotations lack: cost (10 credits, Tier 1) and the POST endpoint. It says nothing, however, about whether drawn cards are deterministic given a seed, or how reversal handling works.

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 one line and front-loaded, and the bracketed group/endpoint/cost lines are terse structured metadata rather than prose. But the brevity reflects under-specification rather than economy – there is essentially nothing beyond a spread size and an endpoint.

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-shape explanation is fairly excused, but for a 6-parameter divination tool the description never explains what the seven positions mean, whether an optional question is required for a meaningful reading, or how this tool differs from its numerous siblings. An agent can invoke it but not confidently choose it.

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 description coverage is only 50%: art, fields and precision are documented in the schema, while question, seed and allowReversed (which defaults to true) have no documentation anywhere. The description provides zero parameter information to compensate, and for a 6-parameter tool with an undocumented question field this is a meaningful 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?

"7-card relationship dynamics" states the resource (a relationship-oriented tarot draw) and the spread size, but omits the verb and gives no basis for choosing it over near-identical siblings such as astroway_tarot_rider_waite_draw_love_triangle or astroway_tarot_lenormand_draw_relationship. The tool family and deck are only recoverable from the bracketed metadata, not from the sentence itself.

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?

There is no when-to-use, when-not-to-use, or alternative guidance at all. With dozens of sibling draw tools (draw_single, draw_three_card, draw_celtic_cross, draw_love_triangle, draw_chakra, draw_horseshoe), an agent has no stated rule for preferring the 7-card relationship spread over any of them.

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