get_performance

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

Far beyond the readOnlyHint/openWorldHint annotations: it discloses the 90 s cap, the load-wait, the blocking interaction with captures, the temporary lifting of the frame-rate limiter (and that a playing fixed-time-step stage runs faster than real time meanwhile), the release of a prior capture's render, and the built-in warnings for >10% variance and eco mode. The only slight tension is that readOnlyHint=true while the tool has transient environmental side effects (limiter state, discarded capture render) — not a data mutation, so not a contradiction, but the description is what makes that nuance visible.

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?

Dense but well organized: purpose, then usage, then side effects, then interpretation caveats. Every sentence carries content, though the metrics enumeration in the first paragraph is long and a few phrases are awkward ('the GPU's render time a frame', 'the conditions to compare two answers by'), costing some readability.

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 measurement tool with an output schema (so return shape needn't be explained), it covers what an agent needs to call it correctly: prerequisites, isolation requirements, timeout, machine-specificity of results, and how to tell when the numbers are untrustworthy. Nothing material is left implicit.

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% and the schema already explains both parameters in nearly the same words ('app updates to let pass first, once the stage has loaded, so shaders and caches settle'). The description reinforces that the warmup precedes measurement and adds the 90 s overall cap, but adds no format, tuning, or interaction guidance for the two parameters beyond the schema — baseline 3 applies.

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?

Opens with a specific verb and resource: 'Measure how fast the Kit app runs the open stage', then enumerates exactly the metrics produced (FPS/frame time percentiles, GPU render time, physics step timing and sim-to-real ratio, GPU memory, prim/mesh/instance counts, render products, and the conditions for comparison). It is clearly distinct from siblings like get_mesh_stats or get_sim_state, which cover only a slice of this.

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 an explicit trigger ('check a frame-rate target, such as 15 FPS with a robot's sensors on'), a precondition ('Play the simulation first... a stopped timeline gives no physics numbers'), and an exclusion ('Measure alone: a capture called meanwhile waits for the measurement, and any other call's work counts in its frames'). This is the rare case where when-to-use, how-to-prepare, and what-not-to-do are all stated.

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