Return the public evals dashboard for a rolling window. Figures are estimated unless provenance.measured lists them. jobs_dispatched_30d and active_providers are null until a measured integer exists — not posture copy. No API key required.
| Name | Required | Description | Default |
|---|---|---|---|
| period | No | rolling_30d |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that figures are estimated unless provenance.measured lists them, and that certain fields are null until a measured integer exists, which is valuable behavioral context. It also states no API key is required, which is a transparency point. No contradiction with annotations (none provided).
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 three sentences, each adding value: purpose, estimation caveat, and null-field behavior. It is front-loaded with the main purpose and avoids fluff. 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?
Given the tool has only one parameter with an enum and no output schema, the description covers the key aspects: what it returns, the estimation caveat, null behavior, and authentication. It could be more complete by explaining the period values, but for a simple tool with no output schema, it is reasonably complete.
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%, so the description must compensate. The description mentions 'rolling window' and the period parameter is an enum with three options, but the description does not explain the meaning of each period value or how it affects the output. It adds some context by mentioning the rolling window, but not enough to fully compensate for the lack of schema descriptions.
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 returns the public evals dashboard for a rolling window, with a specific verb ('Return') and resource ('public evals dashboard'). It distinguishes from siblings by specifying 'public' and 'rolling window', though it doesn't explicitly name alternatives.
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 implies usage for retrieving public evals data over a rolling window, and notes that no API key is required, which is a usage prerequisite. However, it doesn't explicitly state when to use this tool versus alternatives like dispatch.estimate or dispatch.index, nor does it provide exclusions.
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 serves a clearly distinct purpose: readiness probe, cost estimation, evals metrics, trade catalog, order creation, and instant quotes. The overlap between dispatch.estimate and dispatch.quote is explicitly disambiguated by authentication and purpose (keyless rate-card vs. authenticated quoted price), so there is no boundary confusion.
All tools follow a consistent dotted-prefix pattern: agentic.readiness_probe and dispatch.*, with dispatch tools all using a noun-style verb (estimate, evals, index, order, quote). No mixed conventions or irregular verbs; the naming fully supports discoverability.
Six tools is a well-scoped set for a field-service dispatch server. Each tool covers a distinct operational function without redundancy, and the count is neither too thin nor bloated for the declared scope.
The server covers pricing (estimate/quote), order creation, trade catalog, readiness probe, and performance metrics. A minor gap: there is no direct tool to fetch order status or manage/cancel orders, though a tracking URL is returned, which slightly limits lifecycle coverage.
