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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: a 366-day hard cap that is refused rather than truncated (explicit error semantics) and a 20-credit Tier 2 cost. It stops short of documenting other failure modes, but the refusal-vs-truncation disclosure is exactly the kind of non-obvious trait that matters.

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 tight sentences with the purpose front-loaded, followed by a compact bracketed metadata block for endpoint, required params, and cost. Nothing in the prose is wasted; the metadata block is largely contextual scaffolding rather than description, which slightly dilutes an otherwise exemplary structure.

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?

The tool is complex (8 params, an enum activity, output schema present), so return values correctly need no explanation. Still, with 25% schema coverage the definition leaves includeNeutral's semantics and the avoidClashWith value format ambiguous, and it doesn't say how this differs from the sibling single-date Tong Shu tool. Adequate but with clear gaps.

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 25%, so the description has to carry weight and it partially does: it explains both from/to ("walk a date range," cap of 366) and avoidClashWith ("drop the days that clash a person's animal"). However includeNeutral, language, and the accepted value format for avoidClashWith (a 2-12 char animal string?) are undocumented in both places, leaving real gaps.

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?

"Walk a date range and return the days the almanac endorses for one activity, each with the officer that decided it" gives a specific verb (walk/return), resource (Tong Shu almanac days) and unit of output. It is far clearer than a tautology, but it never names its nearest sibling astroway_chinese_tong_shu (single-date almanac) or the many astroway_vedic_muhurat_* alternatives, so the agent must infer the split.

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?

The description explains what the tool does but not when to reach for it over the single-date astroway_chinese_tong_shu or the Vedic muhurat family. The only conditional statements are param mechanics ("optionally drop days that clash") and a hard range cap, which are constraints rather than usage guidance. No exclusions or alternatives are offered.

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