Run Actions

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

Goes well beyond the annotations: it discloses the 50-action cap, that the batch commits as a single undo step, that the whole batch rolls back on the first failure, and what dry_run actually does (roll back and return the verification block). The annotations only flag destructive/non-idempotent; the atomicity and rollback semantics are the crucial behavior an agent needs before mutating a Revit model.

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 sentences, no filler, and the most consequential fact (atomic rollback) is front-loaded. Every clause earns its place.

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?

With an output schema present, return values need not be described, and the description covers the risky batch semantics well. What is missing is routing context against the many sibling action/batch tools, which matters given how crowded this namespace is.

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 only 33%, so the description should carry more weight, and it does explain dry_run's real behavior and the 50-step ceiling for `steps`. However, the `document` parameter (targeting among multiple open documents) is left entirely to the schema and gets no treatment in the description.

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: execute a batch of up to 50 model actions in one atomic step. The scope (batch execution) is clear enough to separate it from the single-action siblings like revit_move or revit_delete, but it never explicitly names those alternatives or the batch-job siblings (revit_batch_start).

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?

Usage is only implied: an agent can infer 'use this when you have multiple actions to apply atomically,' but the description never says when to prefer this over the single-action tools or over revit_batch_start/revit_execute_code. No prerequisites or exclusions are given.

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