find_expensive_nodes

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

With no annotations, the description carries the full burden, and it discloses the crucial non-obvious side effect: the tool records a performance profile while force-cooking display outputs under root_path, i.e. it actively triggers cooks rather than passively reading. It also explains that cook_ms is cumulative so parents include children, which is essential for correct interpretation.

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 purpose, then the mechanism, then the metric caveat, then args. The opening phrasing is slightly editorial but every sentence adds usable information with little waste.

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 no-annotation, no-output-schema, three-parameter profiling tool, the description covers purpose, mechanism, metric semantics, and all params. It stops short of describing the exact shape of the returned ranked list, but that gap is minor.

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 0%, so the description must compensate, and it does: root_path is described as a geo container or '/' broadly, frame as an optional jump before cooking, and limit as the max nodes returned. This meaningfully exceeds the bare schema defaults.

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?

Specific verb+resource: it profiles cooking and ranks the most expensive nodes. It clearly distinguishes itself from passive introspection siblings like get_cook_chain or get_cook_status by being the active hotspot finder.

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?

Frames the use case well ('how a senior artist finds the slow node instead of guessing') and explains the cumulative cook_ms comparison logic for locating hotspots. It does not name explicit alternatives or state when NOT to use it, so it falls just short of a 5.

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