Get network performance

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

The description explicitly states 'Read-only' and 'changes nothing,' reinforcing the existing annotations (readOnlyHint=true, destructiveHint=false). It goes beyond annotations by detailing the return shape and ordering behavior ('slowest node first'), adding valuable context about what the tool produces without modifying state.

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 tightly packed sentences deliver all critical information: read-only nature, recursive behavior, ordering, frame-budget warnings, return shape, and explicit usage alternative. No wasted words; information is front-loaded.

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?

The description is complete for this tool: it covers purpose, usage, behavioral guarantees, and parameter implications. The output schema already documents the return structure, so the description's mention of key fields is sufficient. It also appropriately cross-references the alternative tool, making the decision context clear.

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 parameters are already documented. The description adds semantic context by mentioning 'recursively by default' (matching the recursive parameter) and 'warn about nodes that exceed the frame budget' (linked to target_fps). This enriches the parameter understanding without being fully redundant.

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 clearly states a specific action: 'report cook times under a network (recursively by default, slowest node first) and warn about nodes that exceed the frame budget.' It also distinguishes itself from the sibling tool optimize_performance by explicitly contrasting measurement-only behavior with suggestion/auto-shrink functionality.

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?

Provides explicit when-to-use guidance: 'Use this to just measure; use optimize_performance when you want suggestions and the option to auto-shrink the slow TOPs.' This clearly separates the tool from its closest alternative.

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