performance_snapshot

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the "Read-only" label largely restates structured data. The added value is modest: it names the captured metrics, but says nothing about sampling behavior, cost, or whether the snapshot is instantaneous vs averaged.

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 short lines, correctly front-loaded with the read-only marker before the payload description. No filler sentences.

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 zero-param inspect tool the description covers what data comes back, which is important since there is no output schema. However, in a dense sibling cluster it omits the differentiation and the granularity/cost of the snapshot, leaving a meaningful gap.

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?

The tool takes zero parameters and schema coverage is 100%, so no parameter explanation is needed. Baseline 4 applies for a correctly no-arg tool.

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 resource (performance snapshot) and enumerates exactly what it reports: draw calls, triangles, instanced meshes, object counts by type. An agent understands the output, but the description never distinguishes it from close siblings like perf_monitor, draw_call_breakdown, or memory_stats.

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?

There is no when-to-use guidance and no reference to alternatives. With siblings perf_monitor, draw_call_breakdown, and memory_stats occupying adjacent territory, the agent is left to guess which performance tool to call.

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