List incidents
The global incident feed, newest-first, cursor-paginated.
| Name | Required | Description | Default |
|---|---|---|---|
| host | No | Filter to one host's incidents. | |
| limit | No | Page size, clamped to [1, 200]. Defaults to 50. | |
| since | No | Only include items at or after this ISO 8601 instant. | |
| cursor | No | Opaque pagination cursor returned as `next_cursor` by the previous page. | |
| status | No | Filter by incident lifecycle state. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnly annotation already signals safety, and the description adds useful behavioral details: global scope, newest-first ordering, and cursor pagination. This goes beyond the annotation and helps the agent understand the tool's operational behavior without needing to inspect schema details.
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 extremely concise, front-loading the purpose ('List incidents') and adding only essential qualifiers in a compact form. Every word earns its place, making it easy to parse quickly.
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 read-only annotation, complete schema, and simple list operation, the description provides adequate context for invocation: it names the global feed, ordering, and pagination. It does not describe the return structure, but since there is no output schema, this is a minor gap; overall, the tool is well contextualized.
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 input schema covers all parameters thoroughly (100% coverage), so the description adds little parameter semantics. The description's 'newest-first' and 'cursor-paginated' align with the limit and cursor parameters, but these are also inferred from the schema, so no extra value beyond baseline.
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 lists incidents, with specific qualifiers: global feed, newest-first, cursor-paginated. This distinguishes it from sibling list_host_incidents by emphasizing the global scope, making the purpose unambiguous.
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 provides clear context: it is the global incident feed, so the agent knows to use this for all incidents. It does not explicitly exclude alternatives or mention host-specific listing, but the 'global' qualifier alone implies the appropriate use case.
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.
Most tools are cleanly separated by resource type: participants, access points, hosts, providers, incidents, anomalies, and SLA each have their own get/list vocabulary. The main ambiguous pairs are get_provider_sla vs get_provider_sla_by_key, list_providers vs list_public_providers, and get_summary vs get_network_summary.
The overall get_/list_ verb_noun pattern is consistent and readable, and plural/singular resource names are mostly clear. There are a few exceptions: get_provider_sla and get_country_providers return collections despite using get_, and list_provider_certs is more of an aggregate posture endpoint than a simple list.
43 tools is well beyond the typical well-scoped MCP surface and will make the tool set harder for an agent to navigate defensibly. The tools are systematically grouped, but this looks like a broad REST API surface rather than a compact, purpose-fit MCP server.
For a read-only monitoring and directory domain, the coverage is unusually complete: list/detail endpoints, histories, SLA tables, churn breakdowns, anomalies, incidents, adoption aggregates, software landscape, and quality checks are all represented. The drill-down routes such as churn totals to churn participants also avoid dead ends.
