Generate Numerology Report (PDF or HTML)

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

Annotations already declare a non-readonly, non-idempotent, open-world write. The description adds real behavior beyond them: `pdf` stores a file and returns a url while `html`/`markdown` are not stored, price is identical across formats, no AI is involved, and a non-Latin name yields a 400 NAME_NOT_LATIN rather than being silently zeroed. Missing are retention/lifetime of the stored PDF and any rate-limit 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?

It is a single dense paragraph but front-loaded with the deliverable and its contents before moving to constraints, cost and error behavior. Nearly every clause carries information; only the enumeration of report sections is long, and that enumeration is what makes the output scope legible.

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?

With an output schema present the definition needn't describe return values, and it still covers format/storage semantics, error codes, language fallback and the premium cost warning. The remaining gap is routing guidance against the sibling aggregate report tool, which an agent would still have to infer.

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 57%, but the description compensates for the important gaps: it explains the name must be A–Z with diacritics dropped and other letters refused, that `system` selects one of five letter tables/defaults to pythagorean, and that `language` only truly supports Ukrainian and English with English fallback. The `year` parameter (personal-year chapter, defaults to current UTC year) is only documented in the schema, not the description.

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 names a specific resource and deliverable ('A numerology reading as an A4 PDF (default), HTML or Markdown') and enumerates the exact sections produced (Life Path, Expression, Soul Urge, Personality, Birthday, Maturity, Balance, pinnacles/challenges, personal year). It also distinguishes itself from the per-position siblings by stating it is the whole report built on the same engine as /numerology/{system}/*, so an agent can tell it apart from astroway_numerology_chaldean_balance etc.

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?

It gives actionable invocation context: default format is PDF, the name must be Latin and is rejected otherwise, unsupported languages fall back to English, and it explicitly flags the premium price with 'Confirm with user before invoking.' It does not, however, say when to pick this over the sibling aggregate tool astroway_reports_generate or the individual numerology endpoints beyond noting the shared engine.

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