Estimate public missed-call leakage for a restaurant using Settro's public calculator model.
| Name | Required | Description | Default |
|---|---|---|---|
| pos_system | No | ||
| calls_per_week | Yes | ||
| average_order_value_usd | No | ||
| missed_call_rate_percent | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It mentions using a public calculator model, indicating a calculation, but doesn't describe the return value, side effects, prerequisites, or limitations. This is insufficient for a tool with no output schema.
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?
A single, focused sentence that gets straight to the point. No extraneous 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?
With four parameters, no output schema, no parameter descriptions, and no usage details, the description leaves the agent without essential retrieval and invocation information. It covers the basic purpose but omits return format, parameter meanings, and any modeling assumptions.
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 schema has four parameters with no descriptions (0% coverage). The description mentions none of them, so it adds no meaning beyond the schema's types and constraints. The agent cannot determine what each parameter represents or how they affect the estimate.
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 explicitly states the action ('Estimate'), the specific metric ('public missed-call leakage'), the target ('restaurant'), and the method ('Settro's public calculator model'). This clearly distinguishes it from sibling tools about readiness, options, and summary.
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 explicitly discuss when to use this tool versus alternatives. However, the specific purpose implies its use for estimating missed-call leakage, so some guidance is implied, but no exclusions or alternative tool references are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct aspect of the sales funnel: readiness rubric, recovery options, loss estimation, and overall fit summary. No two tools overlap in purpose, and descriptions clearly differentiate their outputs.
All tool names follow a consistent verb_noun pattern (assess_, compare_, estimate_, generate_), with descriptive noun phrases. The convention is uniform and predictable.
Four tools is well-scoped for a sales-focused server, covering the key evaluation steps without bloat. Each tool serves a specific, non-redundant function.
The set covers the main stages of qualifying a restaurant for Settro: readiness scoring, loss quantification, recovery comparison, and final fit summary. A minor gap is the lack of a tool for actual outreach or follow-up, but the core assessment lifecycle is complete.
