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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), so the bar is lower. The description still adds real behavioral context: the document is pinned by a test to never disagree with the JSON endpoint, and it enumerates exactly what each page carries, including the auspicious first-wear day found by scanning. It omits cost/credit behavior and any storage or retrieval detail.

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 output format and the sibling relationship are front-loaded, and the subsequent inventory of document contents is genuinely informative rather than filler. There is some flourish ('What the document adds is what a table cannot carry'), and the enumeration is long, which keeps it from a 5.

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 explained, and the description instead covers document composition, the determinism guarantee, and the format switch. For a 7-parameter premium report tool it is largely complete, though it says nothing about the drawing-down of credits or the unmentioned localisation/whitelabel options.

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?

With schema coverage at 43%, the description is expected to compensate, and it does add meaning for some parameters: 'same two schools' clarifies the `school` enum, and the 'next auspicious day to first wear it' scan relates to `wearingFrom`. However, `language`, `whitelabel`, `fields` and `precision` are never addressed, so the compensation is partial.

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 identifies a specific resource (the ratna/gemstone prescription) and output form (multi-page A4 PDF by default, HTML with `?format=html`), and explicitly distinguishes it from the data sibling by stating it carries the same astrology as `POST /vedic/gemstones` but adds what a table cannot. The opening is a noun phrase rather than an explicit 'generate' verb, and it does not distinguish itself from other report siblings, so it falls short of a 5.

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 relationship to `POST /vedic/gemstones` is stated (same result, richer document), which implies when to prefer this tool, but no explicit when-to-use/when-not-to-use rule is given. The premium cost and 'confirm with user' caution live in context signals, not the description text, so routing guidance is only implied.

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