Generate Natal Report (PDF or HTML)

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

Annotations declare readOnly=false, destructive=false, idempotent=false, openWorld=true, so the safety profile is partly covered; the description adds material context beyond that: a credit cost of 5,000 (10,000 with depth:extended), a premium-budget warning, and the fact that extended text is pre-edited with no AI at request time. What's missing is any mention of failure modes (invalid house system letters, lat/lon rejections) or whether the whitelabel branding must be pre-configured.

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 output format and document contents, then options, then language and cost — a sensible priority order with no filler sentences. It is dense but each clause carries information; the only waste is the misleading language clause.

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 credit/depth model is well covered. But three of seven parameters (tone, length, enrich) are undocumented and the format flag and language range disagree with the schema, leaving an agent unable to configure the call fully from the description.

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 description coverage is only 29%, so the description must carry the load, yet it leaves tone, length and enrich completely unexplained and references a `?format=html` query flag that does not exist as a schema parameter. It also states 'Languages: uk (default) or en' while the schema enum permits 21 languages and the depth description cites 20 languages — a contradiction that could cause an agent to wrongly rule out valid values.

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 concrete verb+resource ('Render a Western tropical natal chart') and specifies the artifact (single-page A4 PDF, or live HTML). It enumerates the document's contents (Big Three, planets table, house cusps, aspects), which is genuinely differentiating. It does not name the nearest siblings (astroway_reports_ai_natal_narrative, astroway_reports_generate) explicitly, though 'no AI at request time' gestures at the AI-narrative alternative.

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?

The cost line provides a real guardrail ('Premium — ~50% of free monthly budget. Confirm with user before invoking'), which is actionable usage guidance. However, there is no statement of when to pick this over the many sibling report tools (AI natal narrative, reports_generate, reports_love/career), so the routing decision 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.