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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds genuinely new behavioural facts they cannot express: the 5,000-credit Tier 7 price, its magnitude (~50% of the free monthly budget), a user-confirmation requirement, the POST endpoint, and the dependency on the authenticated user's stored white-label config.

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?

Three tightly written sentences: the render action and theming source come first, the chart/fallback fork second, cost metadata last. The cost warning is bolded and front-loaded in its own block so an agent cannot miss the budget impact. No filler sentences.

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 safety, cost and fallback behaviour are all covered. The remaining gap is shape: `chart` is typed as an unconstrained anyOf, and the description says only 'your own birth data' without indicating the expected object structure, so an agent still cannot construct that argument confidently.

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 50%: `fields` and `precision` are documented in-schema, while `chart` has an empty anyOf and no type at all. The description rescues the critical case by explaining what `chart` does and what happens when it is omitted, which is the single most important semantic to convey. It adds nothing for `language`, though the enum is self-describing.

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?

Opens with a specific verb+resource+scope: 'Render a sample natal report PDF using the authenticated user's white-label configuration (colours, font, footer, logo).' The word 'sample' plus 'white-label configuration' cleanly separates it from astroway_reports_natal (real report generation) and from the many astroway_render_* chart tools, which draw charts rather than themed PDF reports.

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 an explicit behavioural fork — 'Pass `chart` to use your own birth data; omit to use the bundled Kyiv 1990 sample' — and the cost banner instructs 'Confirm with user before invoking.' This is clear invocation context, but no sibling alternative is ever named (e.g. astroway_reports_natal or astroway_whitelabel_config), so it falls short of the when/when-not/alternatives ideal.

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