impactplot

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

Annotations declare readOnlyHint=true, so the agent knows this is a read-only visualization. The description adds no extra behavior beyond the schema, but the 'detail' parameter in the schema already explains payload depth for different call contexts (e.g., 'agent' includes violations and next_steps), which is useful behavioral context. Since annotations cover the safety profile, and the schema provides key behavioral detail, the description's limited added value is acceptable.

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 a single clear sentence that front-loads the tool's purpose. It avoids redundancy with the schema and annotations. Extremely concise and to the point, earning the full score.

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, 1 required) and the presence of a rich output schema and comprehensive parameters, the description is sufficient. It names the plot type and uses the schema to detail all parameters. The absence of explicit return-value descriptions is compensated by the output schema. The description could mention expected input format for 'result' but the schema's description of 'result' covers that.

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 100%, and the description itself doesn't add much beyond naming the plot type. However, the schema's 'detail' and 'as_handle' parameters are well-described, and the 'type' parameter has clear enum descriptions. The description's mention of '3-panel plot' helps interpret the 'type' parameter's default 'all'. The baseline of 3 is elevated because the schema descriptions are rich, and the description complements them with the plot style.

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 states a clear verb ('visualization') and resource ('Causal Impact'), explaining it produces a Google-style 3-panel plot. It is distinct from the many sibling plotting tools (e.g., synthplot, did_plot) because it explicitly names 'causal impact' and the Google-style format, though it could be more specific about what makes it unique versus other causal plotting tools.

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?

The description does not mention when to use this tool versus alternatives, but the input schema's 'type' parameter and 'detail' parameter implicitly guide usage (e.g., 'agent' detail for planning next steps). However, there is no explicit guidance on when to choose impactplot over something like synthplot or did_plot. The tool's name and description are self-explanatory for an agent with causal impact context, so this is a minor gap.

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