Upload a CityJSON file

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

With no annotations supplied, the description carries the full disclosure burden and does more than most: it states the interaction happens in-chat via a picker, that the bytes are streamed 'outside the model context,' and that no project folder or workspace setup is required. What it omits is the outcome side — whether the call blocks on user selection, what happens if the user cancels, and whether the file becomes server-visible afterwards.

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?

Four short sentences, front-loaded with the action, then the when-to-use condition, then the transfer mechanics. Nothing is padding, though the workspace/setup sentence is the weakest and could be folded into the transfer note.

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?

There is no output schema and no annotations, so the description is the only source of truth, and it stops short of saying what the call returns or what state the file lands in (upload handle, server-side object, or nothing). For an interactive UI-triggering tool that is a meaningful hole, even though the interaction model and precondition are well covered.

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 coverage is 100% for the single parameter, so the baseline is already high. The description still adds purpose the schema lacks justification for: the question is 'passed' so 'the app can continue after upload,' explaining why a question string accompanies a file transfer. It could have added whether the question is required in practice despite being optional.

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 and resource: 'Open an in-chat file picker to upload a CityJSON file directly.' An agent immediately knows this is an interactive upload entry point rather than a server-side ingest. However, it never distinguishes itself from the closely named siblings cityjson_upload_start/_chunk/_finish or from cityjson_import, so the boundary has to be inferred.

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 gives an explicit triggering condition: 'Use this when the user attached or wants to choose a file that is not visible to the MCP server.' That is a real discriminator against server-visible import paths. The gap is that the chunked-upload siblings are never mentioned as alternatives or as a follow-on chain, leaving the agent to guess whether this single call replaces that flow.

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