preview_control

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

With no annotations provided, the description carries the full behavioral burden and does disclose meaningful traits: it preserves dirty scenes (won't discard unsaved work), refuses other running scenes (a precondition/guard), and only stops this config's preview. What is missing is any explanation of what start vs capture vs stop actually do and what permissions or side effects each entails.

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?

It is only two sentences, but the second is a run-on clause stack ("Preserves dirty scenes, refuses other running scenes; stop only this config's preview before another stage") whose meaning is hard to parse. It is reasonably front-loaded but unstructured for the amount of behavior it tries to convey.

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?

Although an output schema exists (so return values needn't be described), the tool is a 3-parameter stateful control operation with no annotations and 0% schema coverage. The description omits action semantics and parameter meanings, leaving significant gaps for an agent to act on start/capture/stop correctly.

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%, so the description must compensate, but it leaves parameters largely unexplained. The action enum (start/capture/stop) is never mapped to behavior, the sample boolean is not mentioned at all, and config_path is not described. The scattered mentions of "capture" and "samples" do not fully document the three parameters.

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 specific resource and context ("a current saved scene in Play Mode") and mentions capturing screenshots, advancing frames and performance samples, which conveys the general intent. However, it never explains the start/capture/stop action model central to a tool called preview_control, and it does not distinguish itself from siblings like stage_start or standalone_launch. The purpose is broadly inferable but not crisp.

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?

The description gives operational constraints ("refuses other running scenes", "stop only this config's preview before another stage") but never states when an agent should choose this tool versus the sibling stage/job/review tools. There is no explicit when-to-use or when-not-to-use guidance, only implicit context.

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