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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false), and the description adds genuinely new behavior: no extraction, solver run or inferred fields; a 64 MiB combined-data cap; fragment-preserving viewer_url usage; and an async path that may return a pending operation_id instead of a result. The only gap is that it never clarifies what state persists on the server (viewer artifact lifetime, whether the workspace can be re-fetched later), which matters for a readOnly-flagged tool whose output is a URL.

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 operation and constraints, then prerequisite, then limits, then async handling in workflow order. Dense but nearly every clause carries operational weight; the pressure/velocity field detail and the 'qualification and provenance remain visible' remark are the only mildly expendable additions.

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 two-parameter tool with an output schema, this covers what the schema cannot: prerequisites, data provenance restriction, size cap, how to consume viewer_url, and the asynchronous pending-operation loop. Nothing an agent needs to call it correctly or handle its non-final response is missing.

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 50%; the artifact_ids parameter is documented in schema, and the description adds real meaning by specifying 2–8 items, that all IDs must come from the same simulation, and that they must be engineering-view IDs produced by view_simulation_result rather than raw simulation files. The title parameter (default, max length) receives no attention in the description, so the coverage gap is only partly compensated.

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 concrete verb (combine) plus the exact resource (surface, section and streamline view artifact IDs from the same simulation) and the output artifact (one interactive browser workspace with selectable views and pressure/velocity fields). An agent can distinguish it from view_simulation_result and assemble_mesh_viewer without opening either 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?

Explicit prerequisite chain: 'First prepare each with view_simulation_result, completing pending operations,' and an explicit source restriction: 'Use returned engineering-view artifact_id values, not raw simulation files.' It also routes the async case to get_operation with a specific retry cadence and warns 'Do not resubmit to check progress.'

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