sensitivity_plot

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. However, the description adds no behavioral transparency beyond the verb 'Plot' – it does not mention what the tool returns, whether it displays the plot, how it handles the required 'sensitivity' input, or any potential side effects (e.g., caching via as_handle). With the bar lowered by annotations, the description still contributes little about the tool's runtime behavior.

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 very short and front-loaded, with only one sentence and no filler. However, 'appropriately sized' for a tool with 15 parameters and complex interplay is questionable – the brevity borders on under-specification rather than purposeful conciseness. It earns the sentence's place but does not provide enough structure for the tool's complexity.

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 (15 parameters, one required), the description is significantly incomplete. It does not explain the plot's purpose, how to interpret it, or what chain of tools may have produced the input. While the output schema covers return values and the schema documents parameters, the description fails to tie them together into a coherent usage picture. An agent would struggle to decide whether this is the right tool without additional context.

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%, with every parameter having a description (e.g., 'sensitivity' is explicitly 'Output from honest_did()'). The description itself adds no parameter-specific meaning, but the schema already provides the necessary semantics, so the baseline of 3 is appropriate.

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 specific verb ('Plot') and a resource ('Rambachan & Roth (2023) sensitivity analysis'), which clearly identifies the tool as a plotting operation for a particular sensitivity method. It does not explicitly differentiate from sibling tools like sensitivity_dashboard or synth_sensitivity_plot, but the reference to the specific paper gives enough specificity for an agent to infer its scope.

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 provides no guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. It simply names the action and resource, leaving the agent to discover through parameter names (e.g., 'sensitivity' from honest_did()) that it expects specific inputs. No explicit usage context is given.

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