Process Many Models

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

Annotations already mark this destructive and non-idempotent, so the bar is lower – yet the description adds genuinely useful behavior: long actions return status=running and jobId, the caller must poll revit_jobs until the original result is returned, and crucially the model may already have been mutated so the action must not be resubmitted. That non-resubmission warning is exactly the kind of context annotations cannot convey.

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?

Two short paragraphs, front-loaded with the workflow before the operational caveats. Sentences mostly earn their place, with only mild redundancy between the jobId polling instruction and the resubmission warning.

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?

An output schema exists, so return-value explanation is not required, and the async/polling story plus the confirmation-token gate are covered. For a tool with 14 undocumented parameters and nested Process/Save/Export/Open objects, though, the description leaves too much of the input contract unexplained to be fully complete.

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 0% across 14 parameters, so the description carries the full burden and mostly fails. It loosely evokes steps, code, exports and save, and mentions confirm_token, but never explains paths vs folder vs pattern vs recursive, dry_run/preview mechanics, exports format options, stop_on_error, or response_timeout_s.

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 states a concrete pipeline with specific verbs and resources: open each model, run steps and C# code, export, save, close. That is far more than a restatement of the name. However, it never distinguishes itself from near-neighbors such as revit_batch, revit_batch_start, or revit_execute_code, so the agent must infer which batch tool applies.

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?

Implicit usage is clear (multi-model batch processing) and there are real prerequisites: in-place saves and code require a confirmation token from the preview response. But there is no explicit when-to-use/when-not-to-use guidance and no routing to revit_batch or revit_execute_code as alternatives, leaving the agent to guess among overlapping siblings.

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