pr_do

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

With no annotations, the description carries the full load and does most of it: it discloses that returns are operation-result JSON, that writes are verified by readback where Premiere allows, and that property/marker writes leave no undo step — a non-obvious mutation hazard. It does not cover error/failure shapes or any permission requirements per operation, so it falls just short of complete.

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 verb and a usage example, then layers exception handling (undo versus no-undo writes) in two tight sentences with no filler. The embedding of JSON literals inline makes it slightly dense to parse but every sentence 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?

For a 2-parameter dispatcher with no output schema, the description supplies what matters: the return is operation result JSON, results may carry undoSteps/undoStackIndex, and reverting has a documented mechanism. The only missing piece is per-operation failure behavior, which is arguably delegated to pr_catalog.

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%, so baseline would be 3, but the description adds value beyond the schema by showing a worked payload ({'operation':'add_marker','args':{'time_seconds':1.5,'name':'Intro'}}) and making clear that args is an open, operation-specific bag governed by pr_catalog. The {expected_undo_stack_index} reference also explains a parameter-like argument the schema never enumerates.

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 — 'Run one Premiere Pro operation by name (see pr_catalog)' — and includes a concrete inline example of the operation/args payload. The word 'one' implicitly separates it from the batch sibling pr_batch, and the closing line 'Prefer this over writing ExtendScript' names the alternative path an agent might otherwise take.

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 routes the agent to pr_catalog for operation discovery, and gives a concrete when/when-not rule: use the undo operation with {expected_undo_stack_index} to revert, but for property and marker writes checkpoint the sequence beforehand because they record no undo step. That is a real precondition, not a generic 'use this to...' statement.

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