find_expensive_nodes

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

With no annotations at all, the description carries the full behavioral burden and does not meet it. It never says whether profiling actually triggers cooks (potentially slow and side-effecting), whether results are cached, how long it may take, or whether it is read-only; 'cooking' hints at execution but the implications are undisclosed.

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?

A single sentence with no filler, so nothing is wasted, but it is under-specified rather than concise. The one clause does not earn its place as a complete definition for a three-parameter profiling tool.

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 tool with three undocumented parameters, no annotations, no output schema, and potentially heavy profiling behavior, one sentence is far too thin. An agent cannot tell what scope it profiles, which frame it respects, or what the ranking output looks like.

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% and none of the three parameters (frame, limit, root_path) are explained. Only a faint implication exists: 'rank' suggests limit controls result count and 'nodes' hints root_path scopes the search, but frame — the most consequential argument — is given no meaning at all.

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 gives a specific verb pair ("Profile cooking and rank") tied to a clear resource (nodes), and the cost-ranking angle distinguishes it from siblings like find_nodes and find_error_nodes. It loses a point only because "cooking" is domain jargon left undefined, so an agent unfamiliar with the host environment may not know it means evaluating/processing the node graph.

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 guidance on when to reach for this tool versus find_nodes or find_error_nodes, no prerequisites, and no warning about when profiling is inappropriate. The agent must infer that this is a diagnostic tool to run after a scene is built and likely slow.

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