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

The description adds substantial behavioral detail beyond the readOnly/destructive annotations: stable bounded pagination with default and maximum limits, dataset hash retention across pages, and preservation of units, source locators, estimates, and unavailable values. It also states what the tool will not do, which is valuable calibration for an agent.

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 compact and front-loaded: the first sentence states purpose and main filters, the second covers cross-page behavior, and the third clarifies output fidelity and non-transformations. Every sentence earns its place and no redundant filler is present.

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?

Given the 9-parameter schema, the output schema, and annotations already covering safety, the description is complete enough for correct invocation. It covers filter semantics, pagination behavior, output richness, and important exclusions. The only minor omission is naming a fallback tool for aggregation, but that is more of a usability nicety than a correctness gap.

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 description coverage is 0%, and the description compensates by assigning semantic meaning to most parameters: dataset, indicator, geography, category, subgroup, inclusive from/to reference period, and pagination limits. It does not explicitly describe the page parameter by name, though the concept of stable pagination across pages makes its role inferable.

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 uses a specific verb ('Filter') and a distinct resource ('published observations'), then enumerates the exact filtering dimensions: dataset, indicator, geography, category, subgroup, and reference period. This clearly distinguishes the tool from the sibling get_* tools, especially get_market_catalog, which targets catalog metadata rather than observation records.

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 clearly states when to use the tool: retrieving granular published observations matching the given filters. It also draws a clear 'when-not' boundary by explicitly excluding market-size aggregation, unit conversion, and causal inference, preventing misuse. It does not name a specific alternative sibling tool, but the context is strong enough for an agent to route correctly.

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