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

Annotations declare it is a non-read-only, non-idempotent, open-world write, but add nothing about cost or approval. The description fills exactly that gap with a precise price (5,000 credits, Tier 7), a relative-budget warning (~50% of free monthly budget) and an explicit user-confirmation requirement. It does not describe latency or what the returned artifact looks like, but the output schema covers the latter.

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-loads the substantive content list in the first sentence, then a scannable metadata block with group, endpoint, required param and cost. Every element earns its place; the only slight redundancy is restating the required parameter that the schema enforces.

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 paid generative report tool with an output schema, the description supplies the pieces an agent cannot infer: cost tier, budget impact, approval requirement, and the report's thematic scope. The remaining gap is sibling routing (natal vs career vs money reports), which matters given the large reports_* family.

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?

The description only repeats the required-parameter fact ('Required: chart'), which the schema already enforces, and says nothing about fields, language, precision or whitelabel. With schema coverage at 60% and rich nested chart documentation in the schema, the description neither adds meaning nor compensates for the undocumented half; baseline 3 is appropriate.

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?

Names a specific resource (career-themed natal report) and enumerates the astrological content it covers (MC, 10th-house cusp, Saturn, Mars, aspects to Sun), which clearly separates it from reports_natal, reports_money or reports_love. It never states the verb explicitly in the description body (the title carries 'Generate ... PDF or HTML'), but the intent is unambiguous.

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 a framing constraint ('Self-knowledge tool, not directive') and a strong invocation precondition (confirm with user before invoking due to cost). However it never says when to choose this over sibling report tools such as astroway_reports_natal or astroway_reports_generate, so routing among the many report siblings 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.