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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds substantive context beyond that: source attribution with page locators, retrograde flags, degree numbering, substitution logic for toxic/costly/rare stones, and the handling/water/price facts attached to each crystal. What it omits is any statement of input requirements or failure modes.

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 purpose is front-loaded and no clause is empty filler, but the whole definition is effectively one enormous run-on sentence enumerating a dozen output facets. Length is justified by content yet the structure makes it hard to scan; breaking the enumeration from the purpose sentence would help.

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 detailing return contents was not strictly required, and the description is generous there. The real gap is on the input side: a tool requiring either a place string or a full coordinate+IANA timezone set, with an optional offset fallback, gives no guidance on which path to choose — significant for a location-dependent calculation.

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 38% across 8 parameters, so the description needed to compensate and it does not. It never mentions date, time, name, or the anyOf choice between 'place' and the latitude/longitude/timezone triple, nor the timezoneOffset fallback — the most error-prone part of the call is entirely unaddressed.

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 (returns) and a precisely scoped resource: the crystal for each placement's tropical degree per Costelloe's guide, enumerating the bodies covered. It also explicitly separates itself from Jyotish practice and from gemstone prescription, which distinguishes it from siblings like calculate_crystal_timing, lookup_crystal and calculate_relationship_crystals.

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?

It names a context (Western tropical practice, 'separate from Jyotish') and an exclusion ('not a gemstone prescription'), which is implied usage guidance. However, it never states when to call this rather than the clearly overlapping siblings (calculate_crystal_timing, calculate_relationship_crystals, lookup_crystal), so the routing decision is left to inference.

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