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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely non-structured context: the content is AI-synthesised, the payload includes model and period metadata, moon_sign resolution happens upstream, and response_format 'selects JSON vs markdown rendering only' — an important clarification that formatting does not alter content. It does not mention latency, rate limits, or failure modes beyond the external docs link.

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 lead sentence followed by clearly labelled WORKFLOW / INPUT CONTRACT / DO NOT CONFUSE sections, which is easy for an agent to parse. Minor waste: the period enum is re-listed verbatim from the schema, and a docs URL is carried in the description rather than a structured field.

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?

With an output schema present, the description needn't describe return fields, and rich annotations cover the safety profile; what it does provide — sign-name vocabulary, upstream resolution, format-vs-content semantics, sibling disambiguation — is sufficient to call it correctly. The full output and error contract is deferred to an external URL, which leaves error behaviour undocumented in-context.

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 100%, so baseline would be 3, but the description adds real meaning: the full accepted Sanskrit and English moon-sign name lists (the schema only shows one example pair) and the note that resolution is upstream, implying the tool will not validate the sign itself. The restatement of the period enum duplicates the schema and earns nothing.

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 and resource — 'Fetches an AI-synthesised Moon-sign horoscope for a chosen horizon' — and names the return shape (guidance fields plus model/period metadata). It explicitly separates itself from asterwise_get_natal_chart and asterwise_get_gochar, but never distinguishes itself from the close sibling asterwise_get_western_horoscope, nor does it say the horoscope is Vedic/sidereal in the prose (that only appears inside the moon_sign parameter description).

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?

Gives explicit routing: BEFORE None (standalone), AFTER asterwise_get_natal_chart with the condition 'if the user needs a personalised chart', plus a DO NOT CONFUSE WITH block naming two alternatives and the reason each differs. An agent has enough to choose correctly without opening another schema.

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