Performance stats

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

Annotations only say readOnly/openWorld=false; the description adds real behavioral context: it is a sampling measurement that runs 'for a moment', and it discloses the key failure mode that a minimized Roblox window renders no frames, so results would be invalid. It also explains what the 'detail' memory mode changes in the output, none of which is in the annotations.

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 action, then the metric list, then prerequisites. It is dense but nearly every clause carries information; the long parenthetical metric enumeration reads as a run-on and could be tightened without loss.

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?

There is no output schema, so the description carries the return-value burden and does so by enumerating the reported metrics and the 'short notes that say what looks wrong'. Combined with the window-visibility caveat and connection requirement, an agent has everything needed to call it correctly and interpret the result.

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 100%, so the baseline is 3. The description restates the 'memory detail' effect that the enum already documents and says nothing about sample_seconds or client selection beyond what the schema provides.

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 ('Measure how the game performs right now') and enumerates the metrics produced (average FPS, 1% low, frame time, stutters >50ms, physics FPS, memory, ping, network traffic, instance/part counts). No sibling tool covers live performance measurement, so the boundary is clear without opening the 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?

Gives clear usage context — 'right now' signals a live, point-in-time measurement rather than historical inspection — and states two hard preconditions: the game window must be visible and the connected state is required. It does not name alternatives (e.g. screenshot, roblox_status) or say when not to use it, which keeps it below a 5.

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