search-referral-campaignsSearches authorized referral campaigns by name, status, message channel, and bounded performance fields.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of campaigns to return. | |
| query | No | Campaign name, message, or channel. | |
| status | No | Campaign status. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds the 'authorized' scoping constraint, which is useful behavioral context beyond the annotations. However, 'bounded performance fields' is unexplained — it is unclear what performance metrics bound the results or how — and no match semantics (exact vs. fuzzy) are disclosed. No contradiction with annotations.
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 sentence of roughly fourteen words that front-loads the verb and resource before listing filter dimensions. Every word earns its place, and there is no repetition of annotation or schema content.
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?
For a simple search tool with three optional parameters, full schema coverage, and no output schema, the description covers the essential scope and filter dimensions. Gaps include the unexplained 'bounded performance fields' and the absence of any hint about return format (a list of campaigns), but for such a simple read-only tool an agent can reasonably infer the result shape from the tool name and annotations.
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%, so baseline 3 applies. The description lightly reinforces the query and status parameters by listing 'name, status, message channel,' but it introduces 'bounded performance fields,' which maps to no schema parameter, creating ambiguity about what additional filtering exists. The description adds marginal meaning beyond the schema but introduces one confusing term.
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 ('Searches') and resource ('referral campaigns') with clear scope qualifiers: 'authorized' and the filter dimensions 'name, status, message channel, and bounded performance fields.' The tool name and resource type cleanly distinguish it from sibling search tools such as search-broadcast-campaigns and search-reactivation-campaigns.
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?
Usage is implied through the resource type — an agent looking for referral campaigns would naturally select this tool. However, the description provides no explicit when-to-use guidance, no exclusions, and does not name alternatives like search-broadcast-campaigns or search-reactivation-campaigns for the other campaign types.
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.
Tool families are organized by resource and action (get/search/preview/reports), so most tools have a distinct purpose. A few near-overlaps exist—customer-service-requests vs search-service-requests and the many campaign preview/search tools—but descriptions generally clarify boundaries.
The set consistently uses kebab-case with recognizable prefixes like get-, search-, preview-, and reports-, making intent predictable. A few noun-phrase tools (complaint-recall-risk, customer-service-requests, operations-parts, jobs-today) break the verb-first pattern, but they remain readable and grouped.
45 tools is well beyond the 25+ threshold and creates a large surface for agents to navigate, even though the domain is broad. Many tools are narrow read-only variations (e.g., five preview-campaign tools, three reports-* tools), which inflates the count without adding fundamentally new capabilities.
As a read-only/insights server, the surface covers customers, jobs, quotes, invoices, leads, locations, service requests, reviews, campaigns, operations, and reporting with both search and detail access. Minor gaps exist—no get-* for campaign types or social drafts—but these align with the intentionally bounded, safe-read model.