Show Response Curves

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the 'Read-only' restatement is redundant. The description does add genuine context beyond the annotations: mean-null gaps, legacy sparse grid disclosure, the caveat that current spend is not a recommended allocation, and the fact that fixed sections are requested. But it omits output shape details and any rate or auth context.

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 fronted sentence does the work, and the following four short lines each add a distinct behavioral note. The phrase 'Returns the existing JSON unchanged' is slightly cryptic, but overall the description earns its space with little waste.

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?

An output schema exists, so return-value detail need not be spelled out. Yet for a one-param tool with 0% schema coverage, the description gives no hint about what model_hash identifies or how the chart is requested. Useful behavioral notes are present, but the description is not complete for an unfamiliar agent.

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 0% for the single 'model_hash' parameter, so the description could have compensated but never mentions it. The baseline for one param with a bare schema is a 3, and no additional syntax or format information is offered.

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?

States a specific verb and resource: 'Show served response curves, bands and current spend in a native chart.' An agent can identify the tool's function, but the description never anchors it against siblings like show_decomposition or show_optimizer_allocation, which also render model charts.

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 explicit when-to-use or when-not-to-use guidance, and no alternative sibling is named despite a large sibling set containing closely related visualization tools. The mention of 'never accesses prediction-window data' hints at a constraint but gives no positive routing rule.

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