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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful non-annotation context: the 10-credit Tier 1 cost and the Wellness grouping. It says nothing about latency, whether results are cached, or how the sign is derived, but with annotations carrying the behavioral burden a 3 is fair.

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?

Two short lines, no filler, and the payload is front-loaded ahead of the group/cost tags. But the brevity is under-specification rather than efficiency: at 15 parameters and 33% schema coverage, this tool needed more sentences, not fewer.

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 not be described. Everything else is missing: no usage routing against a near-identical sibling, no explanation of why birth data is required for a sign-based lookup, and no parameter detail to offset the 33% schema coverage. For a 15-parameter, 10-credit call, the description is not sufficient to invoke it confidently.

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 33% across 15 parameters, so the description is obligated to compensate and it does not. It explains zero parameters. Most notably, a tool billed as 'by sign' requires date, time, latitude and longitude, and the description never explains that the sign is computed from natal data rather than passed directly — a significant semantic gap for the caller.

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 names the concrete payload (primary + supportive crystals + intentions) and the scoping dimension (per zodiac sign), so the resource is identifiable. However, it uses a noun fragment rather than a verb, and it does nothing to distinguish itself from the near-duplicate sibling astroway_esoteric_crystals_by_zodiac_sign, nor from the broader astroway_esoteric_crystals family. That omission is costly given how crowded this namespace is.

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 routing at all. The '[Group: Wellness]' and cost tags are metadata, not guidance. The absence is especially damaging because an agent has no way to decide between this tool and astroway_esoteric_crystals_by_zodiac_sign, astroway_esoteric_crystals_recommend, or astroway_wellness_herbs.

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