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

Annotations only declare readOnly=false, openWorld=true, idempotent=false, destructive=false. The description goes well beyond them: it discloses the point cost (1 point per storey), the refusal behavior when points or the free month are exhausted, and the 1–3 minute asynchronous runtime. These are exactly the charging/latency traits an agent must know before invoking.

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-loaded with the core action and the cost/latency facts, and every clause earns its place. The opening sentence is dense, packing formats, size cap and storey cardinality into one long clause, which slightly hurts scannability but not correctness.

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?

For a charged, multi-minute, non-idempotent operation with no output schema, it covers cost, duration, failure refusal and how to verify the result. The remaining gap is the immediate return value — it does not say what the call hands back (e.g. a job or sheet id) before the model is ready, and does not warn that re-calling costs points again.

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 all six parameters (including storey, hint, label, language) are already documented. The description adds only the file constraints for file_url and the one-storey-per-sheet rule that implicitly constrains storey; it adds no new meaning for hint, label or language. Baseline 3 is correct.

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 and resource — loads a floor plan from a public https link into a project and starts reading walls, openings and rooms into a measured model. It also scopes the input (PDF/JPG/PNG/WebP, 15 MB, one storey per sheet), so an agent can distinguish it from sibling analysis tools like vedutum_check_floor_plan without opening a 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?

Explicitly covers the when and the when-not: use a direct public https link, but "for a file on the person's computer, give them the upload link from vedutum_get_project instead." It also names the follow-up tool (vedutum_get_project) for checking the result, leaving nothing to inference.

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