Setell pricing report card

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

Annotations already provide readOnlyHint=true and destructiveHint=false, and the description reinforces 'Read-only.' It also adds critical behavioral context: caveats about survivorship, censoring, and small sample sizes that must be repeated when summarizing. This goes beyond the annotations to disclose data limitations and interpretation requirements.

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 dense paragraph that efficiently packs a lot of information (metrics list, usage guidance, caveats). It is front-loaded with the core question but could benefit from clearer structure (e.g., bullet points for metrics). Still, no wasted words.

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?

Despite having no output schema, the description adequately explains what the tool returns by listing the computed fields and their meanings (pointAccuracy, bandCalibration, etc.) and noting caveats. It covers the single optional parameter (via schema) and usage context. Minor gap: the response structure (object keys, nesting) is not described, but the metrics list is sufficient for an AI 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 100% for the single optional parameter (horizonDays). The tool description does not mention this parameter at all, so it adds no additional meaning beyond what the schema already provides. Baseline score 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 clearly states the tool's purpose: to evaluate how right Setell's pricing memory has been by joining draft-time price predictions to real outcomes. It lists specific computed metrics (pointAccuracy, bandCalibration, etc.) and differentiates from siblings like setell_get_pricing_signal and setell_get_margin_summary by focusing on calibration, not raw signals or margins.

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 explicitly provides usage guidance: 'Use when the operator asks 'is my pricing right?', 'how accurate is Setell's memory?', or 'do I lose work when I price high?'. While it doesn't name alternatives or when not to use, the specificity of these questions makes it clear when to invoke this tool.

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