AI Year-Ahead Narrative

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

Annotations only say it is not read-only, not idempotent, non-destructive and open-world; the description adds the material facts an agent actually needs — the POST endpoint, the 250-credit Tier 5 price, and an explicit instruction to confirm before invoking. It stops short of saying how long generation takes or whether repeated calls are billed twice.

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: the first sentence says what the report is, the second what it contains, then a compact inputs line and bracketed metadata for group, endpoint, requirement and cost. The inputs line partly restates the schema, but the defaults and the length hint earn most of that space.

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?

A five-parameter, nested-object, credit-charging tool with an output schema, so return values needn't be explained. The cost, confirmation gate, required parameter and default year cover what an agent needs to call it responsibly; only sibling routing is left unresolved.

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 20% at the top level, so the description must carry weight, and it does: it names all five inputs and supplies information the schema lacks — that year defaults to next year (the schema has no default for it) and that length should be 'long' for a full annual report. The nested chart object is already exhaustively documented in the schema, so no compensation is needed there.

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 deliverable (long-form annual report) and the content it combines: natal context plus the year's outer-planet transits clustered by month. That distinguishes it in substance from a transit-only or natal-only report, but the description never names its closest siblings (ai_monthly_narrative, ai_transit_narrative, reports_transit_yearly), so the agent must infer the distinction.

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 is implied by 'annual report' and 'use long for full annual report', and it adds a real procedural gate: 250 credits, Tier 5, confirm with the user first. However, it gives no guidance on when to choose this over the monthly or plain transit-report siblings, which is the main routing decision an agent faces here.

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