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

Annotations already declare readOnlyHint=true, so the description doesn't need to cover safety. It adds useful behavioral context: the score is a composite, percentile-ranked nationally, and includes trend/confidence/top_drivers/source_lineage. It also notes updates happen on source cadence. No contradictions with annotations.

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 three sentences, front-loaded with purpose and return value, then use cases, then data freshness. Every sentence contributes useful information without redundancy or fluff.

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?

The description covers purpose, use cases, output fields, and update cadence, which is reasonable for a read-only tool with one optional parameter. However, the county-specification gap is a serious completeness issue: without a county parameter or an explanation of how the county is determined, an agent cannot reliably invoke the tool for a specific county. The output schema is absent, but the description mitigates by listing output fields.

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 schema has 100% coverage for the only parameter (days), so baseline is 3, but the description introduces a major ambiguity: it claims the tool works for 'any of 3,222 US counties' yet provides no county parameter in the schema. This suggests a missing mechanism (e.g., implicit context) that the description does not clarify, which could mislead an agent into expecting a county argument. The description adds no extra parameter guidance beyond what the schema already provides.

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 opens with a clear, specific action: 'Returns a 0-100 park-access score for any of 3,222 US counties' and lists the key output fields (score, trend, confidence, top_drivers, source_lineage). This effectively distinguishes the tool from the many sibling adw.* tools by naming the exact resource and metric.

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?

It explicitly states when to call: 'when the user asks about park access, green-space equity, livability, or recreation infrastructure... site selection, parks-bond planning, or recreation grant targeting.' This provides clear contextual triggers, though it does not explicitly mention when not to use it or name alternative tools.

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