Admin only. Delivery quality per carrier/provider/channel, failure codes, DLR plausibility (whether delivery reports can be trusted), and ported-number routing hints. The data behind any provider-routing decision.
| 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, the description carries the burden of behavioral disclosure. It does disclose an admin-only authorization requirement and explains what DLR plausibility means, which is useful. However, it does not state side effects, read-only nature, data freshness, output format, or error behavior, leaving notable gaps for a no-annotation tool.
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 compact and front-loaded with the access restriction, followed by a dense but well-organized list of data dimensions. The final sentence earns its place by framing the tool's strategic purpose without repetition or filler.
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 tool with one optional parameter and no output schema, the description covers the main content areas and access constraints well. It could be more complete by explicitly distinguishing itself from ops_monitoring/ops_pulse or describing the expected response shape, but the current description is sufficient for basic selection and invocation.
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 only parameter, 'days', is fully documented in the schema with range and default (1-365, default 30), providing 100% schema coverage. The description adds no additional parameter detail, so the baseline score of 3 is appropriate since the schema already does the heavy lifting.
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's domain: delivery quality per carrier/provider/channel, failure codes, DLR plausibility, and ported-number routing hints. It distinguishes itself from generic balance/pricing/send tools, and the phrase 'data behind any provider-routing decision' grounds its purpose. However, it lacks an explicit verb like 'retrieves' or 'reports', and does not directly contrast with the sibling ops_monitoring/ops_pulse tools.
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?
'Admin only' sets an access prerequisite, and 'The data behind any provider-routing decision' clearly communicates the intended use case. This gives a clear context for when the tool would be relevant, though it does not state explicit exclusions or alternative tools for non-routing operational monitoring.
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.