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 contributes beyond that by disclosing the endpoint (POST /v1/ziwei/palace-spouse), the required input (date), and a per-call cost of 5 credits (Tier 1/2) — the cost and endpoint are genuinely useful operational context not present in annotations or schema. It says nothing about output shape or determinism beyond what annotations imply.

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?

Very short and front-loaded: the purpose fragment leads, followed by a compact bracketed metadata block (group, endpoint, required, cost) that is easy to scan. Nothing is redundant, though the extreme brevity borders on under-specification rather than disciplined concision.

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, and annotations cover the safety profile. However, for a 6-parameter, cost-bearing calculation tool belonging to a large family of Zi Wei palace endpoints, the description leaves the agent without enough to distinguish this palace from its ten siblings or to understand what the result represents beyond "romantic union".

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 67% and the description's only parameter content is "Required: date", which merely restates the schema's required array. No meaning is added for time, timezone, timezoneOffset, fields, or precision — the schema descriptions for timezone/fields/precision are far richer than anything in the description, so this text adds nothing over the structured fields.

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?

"Marriage partner, romantic union" names the subject domain and, combined with the title "Spouse Palace (Fuqi)", an agent can infer this returns the Zi Wei Dou Shu spouse-palace reading. But it is a noun fragment, not a verb+resource statement, and it never says it produces a palace analysis, so it does not clearly separate itself from adjacent tools like astroway_ziwei_twelve_palaces or astroway_ziwei_full_chart.

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 guidance, no statement of prerequisites, and no named alternative. An agent cannot tell from this text whether to call this or the broader astroway_ziwei_twelve_palaces / astroway_ziwei_chart tools, or how it relates to interpretation tools like astroway_ai_interpret_element.

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