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 does disclose important behavior: it 'Records a performance-monitor profile while force-cooking the display outputs' and clarifies that cook_ms includes parent+child times. This is valuable contextual information beyond the parameter schema, though it omits details like exact response shape or side effects on the scene.

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 description is well-structured and front-loaded with the core purpose, followed by behavioral detail and an Args list. Each sentence contributes useful information, though the analogy 'how a senior artist finds the slow node instead of guessing' is a slight flourish rather than strictly necessary.

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?

Given there is no output schema, the description explains the tool's behavior, parameter meanings, and the key 'cook_ms is cumulative' interpretation rule. It is largely complete for an AI to call and use this tool, though it could provide a little more detail about the exact return structure beyond ranking.

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%, but the description compensates fully by explaining every parameter in the Args section: root_path, frame, and limit. It adds practical semantics such as 'a geo container, or "/" broadly' and 'Optionally jump to this frame before cooking,' which goes well beyond the bare schema.

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: 'Profile cooking and rank the most expensive nodes' with a concrete resource ('display outputs under root_path'). It is distinct from siblings like find_error_nodes and get_cook_chain because it focuses on cost profiling, though it never explicitly names or contrasts with any sibling tool.

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?

It communicates when to use the tool: when a senior artist needs to find the slow node instead of guessing, and it explains how to interpret results by comparing siblings because cook_ms is cumulative. However, it does not explicitly mention alternatives or when not to use this tool.

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