list_datasets

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds useful behavioral context by disclosing what the listing surfaces (row counts, date coverage, masked columns), which matters for a discovery tool, but says nothing about result size or limits.

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?

Two tight sentences: capability first, then the call-first routing cue. No filler, and the most actionable instruction is front-loaded.

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 an output schema present, return-value detail need not live in the description, and for a zero-parameter read-only discovery tool nothing an agent needs is missing. The description supplies exactly the orientation cue required to start a session.

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?

There are zero parameters, so there is no parameter semantics to document; the baseline for a parameterless tool is 4. The description correctly adds no redundant parameter chatter.

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 (List) and resource (available tables/datasets) and even previews the return payload: row counts, date coverage, and masked columns. That framing clearly distinguishes it from data-returning siblings like search_records, get_work_orders, and scrap_summary.

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: "Call this first when you do not know the data." That tells the agent when to reach for it instead of the other siblings, though it names no concrete alternative for the case where you already do know the data.

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