bgp_neighbor_rca

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With only readOnlyHint=true annotated, the description adds real behavior: it pulls get_bgp_neighbors, orders findings worst-first, and each finding cites session state (is_up/is_enabled) or uptime along with a cause and a suggested action. That disclosure of output shape and remediation content goes beyond the annotation, though severity thresholds and handling of an unreachable device are not covered.

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?

Front-loaded with the [READ] tag and the core purpose in the first line, then supporting detail, then args. Every sentence carries information, though the multi-line Args block is slightly heavier than needed for a single self-documenting parameter.

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?

No output schema exists, so the description takes on return-value explanation and does so at a useful level (worst-first findings with state, cause, action). Combined with the default-device parameter semantics, the definition is complete enough to invoke correctly, with only threshold/scoring details left unspecified.

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 carry the parameter. It does explain that target is a device name from config and that omitting it falls back to the default device, which is meaning the schema (a bare nullable string with default null) does not provide.

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?

States a specific verb (flag) plus resource (BGP neighbors) and enumerates the exact fault conditions it looks for (down, shut, recently reset, route-less). It also clarifies its relationship to the sibling get_bgp_neighbors by describing itself as an analysis layer that pulls that tool's data and reports worst-first findings, so an agent can distinguish raw retrieval from RCA.

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 context is implied by the fault-oriented framing (use it when diagnosing unhealthy BGP sessions), and it names get_bgp_neighbors as its data source, which hints at when raw data is preferable. However, there is no explicit when-to-use versus when-to-use-an-alternative rule and no stated prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.