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

Annotations only say readOnlyHint=false and non-idempotent; the description adds real behavioral context beyond them: no AI at request time, the 5000 vs 10000 credit cost of extended depth, and what whitelabel:true changes. It does not disclose rate limits or auth requirements, but the cost/behavior disclosures are substantive for a premium mutation.

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 primary action and outcome, and each sentence carries distinct information (contents, output switch, branding, depth/cost, language). The depth sentence is dense and slightly run-on, but there is no filler.

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 the description covers the premium cost, required chart input, output formats and depth tiers. It does not touch the tone, length, enrich, fields or precision parameters, leaving those schema-only, which is acceptable but not fully complete for a 9-parameter premium generator.

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 only 44% schema description coverage, the description compensates by documenting things the schema omits: the `?format=html` output switch (absent from the schema entirely), the `language` default of uk, and the effect of `whitelabel: true` and `depth: "extended"`. It leaves tone, length, enrich, fields and precision unexplained, so it does not fully close the gap.

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+resource ('Render a Western tropical natal chart') and names the exact deliverable (single-page A4 PDF or live HTML), then enumerates the contents (Big Three, planets table with retrograde, 12 house cusps, aspects). An agent can distinguish this from render-wheel image tools and other report siblings 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?

Usage context is implied through the format and depth options plus the premium-cost warning ('Confirm with user before invoking'), which is genuine guidance. However, it never names when to pick this over sibling report generators (e.g. career/love/natal-narrative reports) or when the HTML variant is preferable, so the when/when-not logic 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.