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

Annotations only cover the safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=true). The description adds materially: the exact cost (5,000 credits, Tier 7), that it consumes ~50% of a free monthly budget, and an explicit instruction to confirm with the user before invoking — the kind of spend/operational context annotations cannot express. It still says nothing about latency or how the rendered document is returned.

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 the core action and output content in the first sentence, then scope constraints, then a bracketed metadata block. Every line carries information, though the [Group]/[Endpoint]/[Required] block partially duplicates what the schema already declares and the endpoint string is of marginal use to an agent.

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 explained, and the description covers report contents, cost, and the required chart. What is left implicit is the delivery mechanism for the rendered document and the PDF-vs-HTML ambiguity raised by the title — small gaps against an otherwise complete brief for a premium report tool.

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% and the schema itself documents chart, fields, precision, and timezone in depth. The description's only real parameter contribution is the non-schema default for `year` (next calendar year when omitted) and a restatement of the required `chart`; it says nothing about language, whitelabel, or compact-mode fields/precision, so it lands at the baseline rather than compensating.

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?

Specific verb plus resource: 'Render a year-ahead transit calendar PDF grouped by month,' with content detail (Mars–Pluto aspects, the five Ptolemaic aspects, 0.5° orb) that clearly identifies this as the printable year-ahead transit report rather than the data endpoints (astroway_prognostics_transit_calendar) or the AI narrative siblings. An agent can tell what it produces without opening the schema. Minor wrinkle: the title says 'PDF or HTML' but the body says PDF only, and no format parameter exists.

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 rather than stated: it is a report-generation call and the cost block warns to confirm with the user first, which is a genuine precondition. However, it never says when to prefer this over astroway_reports_ai_year_ahead_narrative, astroway_reports_ai_transit_narrative, or astroway_prognostics_transit_calendar, nor what prerequisites (e.g., an existing chart) must hold.

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