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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so safety is covered. The description adds real behavioral context beyond that: the underlying methodology (Costelloe's degree table, composite midpoints), the tradition scope (Western tropical), and an explicit epistemic limit ('not a verdict on the relationship'). It does not disclose sensitivity to birth-time accuracy, which matters for a computation keyed on precise degrees.

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?

Front-loaded with the source and subject, then a compact enumeration of what comes back, with the scope caveat last. It is a single dense sentence with no filler, though the run-on list of planets and output types is harder to scan than it needs to be.

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 description covers methodology, planetary scope, and interpretation limits. Given two nested person objects and required birth date/time/location alternatives, it is still missing input requirements and any routing guidance among the crystal/relationship siblings. Adequate but with clear gaps for a tool of this complexity.

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 reported at 0%, so the description is expected to compensate, and it says nothing about personA/personB, required date and time, or the place-vs-coordinates alternatives. It only implies 'two people' via 'for the pair'. The nested schema does carry a few inline descriptions (place, timezone, timezoneOffset), which prevents a 1, but the description adds no parameter meaning of its own.

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 a concrete resource (relationship crystals from Costelloe's degree table), the technique (composite midpoints over Sun/Venus/Mercury/Moon/Mars/Jupiter/Saturn), and the outputs (relationship, communication and emotion crystals, shared colours). An agent can tell this is a two-person crystal synthesis rather than a single-chart one. However, it never explicitly contrasts itself with the very similar siblings calculate_crystal_profile and calculate_relationship_compatibility.

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 statement of when to use this versus the many adjacent tools: calculate_crystal_profile (single person), calculate_crystal_timing, or calculate_relationship_compatibility. The only orienting clause is the disclaimer 'not a verdict on the relationship', which is a caveat, not usage guidance. The agent must infer applicability purely from the tool name.

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