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

Annotations only supply the safety/idempotency profile; the description adds genuinely useful behavior the annotations don't carry: fully deterministic with 0 AI, the cost of 5,000 credits (~50% of a free monthly budget), the need to confirm with the user, and the body-vs-query-string channel rule. It does not say whether the generated report is persisted (reports_history suggests it may be), which is a minor gap.

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 with the deliverable, then the options, then the cost caveat — a sensible order with no filler sentences. The long parenthetical inventory of wheel elements is slightly over-detailed relative to its decision value, but it justifies its space by telling the agent the output is high-detail.

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?

For a 6-parameter tool with a nested `chart` object and an output schema, the description covers the decision-relevant dimensions (format, style, whitelabel, i18n, cost) while the schema handles return shape and chart fields. Only the persistence/handling of the produced artifact is left unstated.

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 50% schema coverage, the schema already carries the heavy lifting for `chart`, `fields`, and `precision`. The description nonetheless adds real value by mapping each `style` enum value to its visual character (editorial=light, celestial=dark+gold, classic=minimal) beyond the bare enum list, and by clarifying that `style` must be sent in the request BODY rather than the query string.

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 artifact ('Render a data-rich, print-ready natal chart poster') and then enumerates the exact contents (western wheel with element sectors, ASC arrow, placements table, balance bars, top aspects). This clearly distinguishes it from image-oriented siblings like astroway_render_wheel_western and from narrative reports. An agent knows precisely what it gets without opening the schema.

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 strong context — PDF is the default, `?format=html` returns HTML, style/whitelabel/language are the levers, and the premium cost carries an explicit 'Confirm with user before invoking' instruction. It stops short of naming alternatives (e.g. reports_natal vs. render_wheel_western), so the when-not-to-use case is left to inference.

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