Heatmap

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

With no annotations, the description carries the full burden, and it does disclose the key side effect: the heatmap is saved and a filename is returned. It does not state where the file is written, what happens if no numerical columns exist, or how non-numeric columns are handled, leaving meaningful behavioral gaps for a tool that writes to disk.

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 core purpose leads, followed by a compact Args/Returns block with no filler sentences. The structure is slightly boilerplate but everything stated is useful and nothing is redundant.

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 two-parameter tool with no output schema, the description covers the invocation inputs and summarizes the return dict (dataset ID, method, columns used, saved filename). Remaining gaps are the save location and edge-case behavior when no numerical columns are present.

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: it explains that dataset_id identifies the dataset and that method accepts pearson, spearman, or kendall with pearson as default. The allowed-value list is genuinely additive since the schema only types method as a free string.

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?

Names a specific verb pair (generate and save) and a specific resource (correlation heatmap of all numerical columns), which tells an agent this produces an image artifact rather than just statistics. It does not name or distinguish itself from likely siblings such as analyze_correlation or auto_visualize, so it stops short of a 5.

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?

Usage is only implied: the agent can infer this is the tool to call when it wants a saved visual correlation matrix. There is no explicit statement of when to prefer this over analyze_correlation (numeric output) or auto_visualize, and no stated prerequisites such as needing at least two numerical columns.

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