Measure per-operator cook costs (ms) to find the most expensive nodes eating frame time. Filter by path or top N results.
Per-operator cook cost (ms) sorted most-expensive first: which device is eating the frame.
paths (list[str]): Operator paths to measure.
path (str | None): Parent whose children are measured.
top (int | None): Return only the N most expensive.
| Name | Required | Description | Default |
|---|---|---|---|
| top | No | ||
| path | No | ||
| paths | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral disclosure burden. It does explain the output ordering and scoping semantics ('Parent whose children are measured', 'Return only the N most expensive'), but it leaves the return shape undefined, neither confirms the operation is non-mutating/read-only nor defines what 'device' means.
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?
The definition is compact and front-loaded: the first sentence conveys the core behavior and purpose, followed by a minimal, scannable parameter list. Every sentence adds necessary information with no filler.
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 three-parameter measurement tool with no output schema and no annotations, the description covers the key inputs and output ordering, which is a solid baseline. However, it leaves gaps around the exact return format, whether path and paths are mutually exclusive, and the precise meaning of 'device' in the output.
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 fully document the parameters, and it does: 'paths' identifies operators to measure, 'path' selects a parent whose children are measured, and 'top' limits results to the N most expensive. This adds real meaning beyond the bare JSON schema, though it does not clarify the relationship between 'paths' and 'path'.
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 names a specific metric ('per-operator cook cost (ms)'), a sorting behavior ('most-expensive first'), and a practical diagnostic goal ('which device is eating the frame'). It is clear about what the tool measures, though it does not explicitly contrast itself with sibling measure_* tools such as measure_gpu or measure_chain.
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 no explicit guidance on when to choose measure_cooktimes over the sibling measurement tools, nor does it explain whether 'paths' and 'path' should be used exclusively or how they interact. The intended use is only implied by 'per-operator' rather than stated as a selection rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.