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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds genuinely non-structured context: the data is collected hourly from the Arkansas Judiciary's official archive and a last-success timestamp is exposed, which tells the agent how fresh an 'absence' answer is.

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?

One sentence enumerating the returned fields followed by a single-sentence usage trigger; no filler. The coverage dimension list is long but every item is load-bearing, and the actionable instruction is not buried.

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 no input parameters and no output schema, the description carries the full burden of explaining return values, and it does so field-by-field at the correct granularity (per court). An agent can decide whether the pack can support a given citation before answering.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline for a parameterless schema is 4. The description spends its space on output content rather than fabricating parameter semantics.

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?

Names a specific artifact (coverage metadata for the Arkansas appellate opinions pack) and enumerates exactly what it reports: per-court counts, earliest/latest decision dates, highest neutral citation per year, revised-opinion counts, and collection freshness. This is immediately distinguishable from sibling tools like ark_search_opinions or ark_recent_opinions, which retrieve opinions rather than describe the corpus.

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?

Gives an explicit trigger condition with a worked example: 'Use before relying on an absence ("is 2026 Ark. 150 out yet?")'. It does not name alternative tools or state when not to use it, but for a coverage-lookup tool the invocation condition is unambiguous.

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