Admin only. Business health snapshot: margin, cash collected, customer float (liability), solvency ratio, active accounts, and money stuck in the refund-review queue.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Lookback window in days (1-365). Default 30. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the transparency burden. It discloses an auth requirement (Admin only) and clearly enumerates the data returned, implying a read-only snapshot. It does not explicitly confirm non-mutating behavior or describe response shape, but for a report-style tool this is strong disclosure.
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, well-structured sentence that front-loads access control and core purpose, then lists concrete metrics. There is no filler or redundant information.
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 snapshot tool with one optional parameter and no output schema, the description covers the key decision-relevant aspects: admin-only access and the complete set of returned metrics. It could mention how the days parameter influences the snapshot, but the schema handles that detail.
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 coverage is 100%, so the baseline is 3. The only parameter, days, is fully described in the schema with its range and default. The tool description adds no parameter-level detail, but the schema already provides sufficient semantics.
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 identifies the tool as a business health snapshot and enumerates the specific metrics it returns (margin, cash collected, customer float, solvency ratio, active accounts, refund-review queue). This is specific enough to distinguish it from siblings like ops_monitoring or get_balance.
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 'Admin only' prefix provides a clear access restriction and implies this is for administrative business health overviews. However, there is no explicit guidance on when to prefer this tool over related siblings like ops_monitoring, nor any 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.
Tools split into clear clusters: customer-facing send/verify/get tools and admin ops tools. The three ops_* tools could initially seem similar, but their descriptions distinguish operational alerts, business health, and route quality. Minor overlap exists between ops_monitoring and ops_pulse, but overall boundaries are clear.
The set uses consistent prefixes: get_, send_, verify_, and ops_. This creates a predictable pattern for agents. Minor deviation is that ops_pulse and ops_route_quality are noun-style rather than verb-noun, and 'pulse' is less descriptive than the others.
Eight tools is well-scoped for an SMS/OTP server, covering customer actions, pricing/balance, and admin oversight without bloat. Each tool has a clear role and the count feels appropriate for the domain.
Core flows are covered: balance lookup, pricing, sending SMS, OTP lifecycle, and admin monitoring. A notable gap is lack of per-message delivery status or send history, but agents can still complete the primary send-and-verify workflows. Minor gaps exist but are workable.