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

Annotations already declare readOnly, idempotent, closed-world, so the safety profile is covered. The description adds real behavioral detail beyond them: the four verdict buckets (fresh/aging/stale/empty), that a verdict reports the number behind it, and that the last collection run's status is included — useful context an agent would not infer from the schema.

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 purpose, followed by a compact enumeration of what is reported and a closing usage directive. The middle clause is dense and list-like but every element identifies a distinct returned attribute; nothing is padding.

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 structure needn't be spelled out, and the description still summarizes the salient outputs and verdict semantics. For a zero-required-parameter read tool, an agent has everything needed to decide to call it and how to interpret the staleness threshold.

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 coverage is 100%, so baseline is 3. The description earns above baseline by framing stale_after_days as 'a staleness line you choose' and connecting it causally to the verdict categories, which the schema does not state as a relationship.

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 verb and resource ('Report how old the data is') and enumerates the exact outputs: newest/oldest observation, age in days, a named verdict, and last collection run status. It is clearly distinguishable from siblings like get_dataset_coverage, which is referenced only for obtaining the city list.

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?

'Call this before quoting a price as current' gives a concrete trigger condition tied to the agent's task. It does not name an alternative tool or a when-not-to-use case, but for a freshness check the positive trigger is the operationally relevant guidance.

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