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

Annotations declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds crucial non-obvious behavior: truncation indicators in the response, pagination via nextOffset, a limit ceiling, deeper-paging limit (offset max 1000) with fallback instruction (download full file). This is rich behavioral context beyond structured fields and absent an output schema, which is exactly what the description must supply.

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-loads the core action, then the required parameter, then pagination behavior, then optional source. Efficient and ordered for an agent. Slightly dense but every clause carries information (defaults, caps, pagination fields, source default).

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?

A read/pagination tool with sibling city_datasets and no output schema. The description covers the required input source, pagination mechanics (truncated/matchingRecords/nextOffset), limits, and the source default. This is complete for correct invocation and continuation without an output schema.

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 100%, so the schema already documents limit (1-50, default 10), offset semantics, search, source default, and dataset_id source. The description echoes the defaults and the limit ceiling but adds no syntax or format beyond the schema. Baseline 3 is appropriate.

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 (read) and resource (one page of records from a public open dataset), and distinguishes from city_datasets by name and role ('Give a dataset_id from city_datasets'). An agent can tell this is the record-fetching tool versus the dataset-listing tool.

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?

Explicitly explains when pagination is needed ('a full page is usually NOT the whole answer') and names the fields to use for continuation ('truncated', 'matchingRecords', 'nextOffset'). Names the dependency on city_datasets for dataset_id. No exclusions but the usage path is fully specified.

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