Export CityJSON from cjdb

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

With no annotations to lean on, the description carries the full transparency burden and does a good job. It discloses that the operation is read-only via 'read-only SELECT-defined subset', and the schema further reinforces this by stating mutating SQL and semicolons are rejected. It also reveals the optional collection behavior and output as a 'CityJSON dataset handle'. This goes beyond merely stating the action, though it could additionally clarify that the export does not modify the database or describe error/edge-case behavior.

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 a single, front-loaded sentence that leads with the core action and primary purpose, then appends the optional behavior. Every phrase earns its place: 'all objects or a read-only SELECT-defined subset' defines scope, 'from cjdb to CityJSONSeq' defines boundaries, and 'optionally collect...handle' defines the output mode. There is no padding, repetition, or irrelevant detail.

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 moderate complexity (a nested connection object, three parameters, and no output schema), the description gives a good overview but leaves the agent without important operational details. It does not explain what the returned 'handle' actually is, how connection credentials are used, or what happens when 'query' is omitted (though 'all objects' implies default). Since there are no annotations or output schema, these gaps are more consequential, placing it at an adequate but incomplete level.

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 only 33% (only 'query' gets description text), and the overall description partially compensates by explaining that the 'query' parameter selects an object_id subset and 'collect' toggles between CityJSONSeq and a normal CityJSON dataset handle. However, the 'connection' nested object remains undocumented in both the schema and description, and the description does not explain the all-objects default behavior with the same explicitness. It adds meaningful context for query/collect but leaves the most complex parameter underserved.

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 clearly states a specific verb ('Export'), a precise source ('from cjdb'), and an output format ('to CityJSONSeq'), distinguishing it from sibling export tools like cityjson_export by emphasizing the database origin. It also names the two operational modes: all objects or a SELECT-defined subset, and the optional collection behavior, leaving no ambiguity about the tool's core function.

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?

The description gives clear context for when to use the tool: exporting either the entire cjdb content or a subset specified by a read-only SELECT query. It also explains the optional 'collect' behavior that changes the output form. However, it does not explicitly contrast this tool with alternatives such as cityjson_export or cityjson_db_import, so it stops short of full when-to-use vs when-not guidance.

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