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

Annotations already cover safety (readOnlyHint, idempotentHint, closed-world), but the description adds context annotations cannot express: the call is free, coverage figures are read live from the database rather than cached, and failures are classified by blocker type with the prerequisite that would lift it. It also implies a cost asymmetry with the other tools, which shapes agent planning.

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?

Three sentences with no filler, and the two most decision-relevant facts — it is free and it should be called first — sit at the start and end where they will be read. The middle sentence is long but every clause (examples, blockers, prerequisites) is a distinct piece of information.

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, the description need not describe return values, and it instead explains what those values mean (answerable classes, runnable examples, blocked classes with lifting prerequisites). The one gap is the boundary against get_dataset_coverage and get_data_freshness, which share the introspection role.

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 and the description correctly says nothing about arguments, so there is nothing to misinterpret. Baseline 4 applies for a 0-param schema; no value is added or lost.

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?

A specific verb+resource: it lists the question classes the dataset can answer (with a runnable example argument per tool) and the questions it cannot, with named blockers. That is plainly a different kind of operation from every sibling (search_*, compare_*, summarize_costs), so an agent can classify it without opening the schema.

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 spending anything" gives an explicit trigger condition plus the cost rationale ("free"), which is stronger than most tools manage. It does not differentiate itself from the neighbouring introspection tools get_dataset_coverage and get_data_freshness, which likely overlap in scope, so routing between those three is left to inference.

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