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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false). The description adds useful context beyond annotations: it discloses the markdown output, the token limit (≤3200 tokens for long), the return of model and token usage, the grounding scope on the computed natal chart, and the heavy cost. It does not describe authentication, failure handling, or credit-charging rules, so a 4 is appropriate.

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?

The description is front-loaded with the tool's purpose and output format, followed by inputs, returns, grounding scope, and cost/group metadata. It is mostly efficient, though listing input options briefly duplicates schema enums; the cost warning and token cap justify their space. No major restructuring is needed.

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?

Given the complexity (AI narrative generation with nested chart input, 6 parameters, output schema present), the description covers the essential invocation concerns: purpose, output format, key input controls, cost, token cap, and grounding scope. The output schema handles return-value details, so the description need not explain them. The main gap is the unmentioned fields and precision parameters, but the schema covers them.

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 50%, so the description must compensate but only partially does so. It names and explains chart, language (21 codes), tone (warm/professional/concise), and length (short/medium/long; ≤3200 tokens), adding useful meaning such as the token cap and language count. However, it omits the fields and precision parameters entirely, and the chart parameter's rich nested schema is not augmented in 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 states a specific verb and resource: 'Long-form natal-chart narrative (markdown).' It clearly distinguishes this tool from sibling AI narratives (monthly, synastry, transit, year ahead) and from non-AI natal report tools by naming the resource as a natal-chart narrative. An agent can identify the tool's purpose 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?

The description provides clear context for use: it is an AI Reports tool costing 250 credits (Tier 5), marked as heavy, and instructs the agent to confirm with the user before invoking. It does not explicitly list when to choose this over other AI narrative siblings or when not to use it, but the cost caution and purpose give sufficient usage context for an agent to proceed carefully.

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