add_error_bars

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

The description does not disclose side effects, whether it overwrites existing error bars, permissions, or potential failure modes. However, it does provide meaningful behavioral context by explaining how the kind parameter changes interpretation (byField vs byPercentage) and instructs to verify the render in Desktop, which gives some operational awareness. Since there are no annotations, more transparency would be expected.

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 concise and front-loaded with the primary action. It efficiently packs many parameter relationships into a compact format. It loses a point for being a somewhat dense run-on structure, which could be more readable with bullet points or clearer separation of ideas.

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 the tool's complexity (11 parameters, no annotations, no output schema), the description covers the core parameter interactions but omits practical context such as when to use the tool, prerequisites, or what happens to existing settings. The instruction to verify in Desktop hints at a render step, but not enough for a fully self-contained understanding.

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?

The description adds substantial value beyond the schema by explaining the relationships between parameters: e.g., byField uses upperField/lowerField from measureTable, byPercentage uses percent, symmetrical is optional, and relation/band have specific enums. This clarifies conditional logic that the schema's per-field descriptions do not capture.

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 the action ('Add ERROR BARS') and the specific target ('the errorBars object' on a chart). It is distinct from sibling tools by naming the exact chart feature, so there is no ambiguity about what this tool does.

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 use this tool versus alternatives, nor any exclusions or prerequisites. The description focuses on configuration details (kind, relation, band) but does not explain the broader use case or when this tool is appropriate compared to other visual-editing tools.

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