bgp

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does add one useful trait: an empty result often means FRR has not been enabled. However, it omits that this tool can mutate system state (configure, create/delete/toggle_neighbor), presumably requires confirmation and staging in some actions, and may have irreversible effects. The description leans on the schema and the help action rather than disclosing these behaviors.

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, only two sentences, and front-loads the domain before the critical empty-result caveat. No sentence is wasted. The first sentence is a fragment and could be a bit more explicit, but it does not bloate the text.

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?

The tool is complex – 15 parameters, 7 actions, no output schema, and no annotations – yet the description provides only the domain, one environment caveat, and a help-action instructon. The rich input schema compensates significantly, and the help action fills gaps. Still, the description does not cover side effects, when to use confirmed/staged flows, or relationship to siblings like 'routing', so it is not fully complete.

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 the parameters are already well-documented in the input schema. The description's pointer to action='help' adds a meta-layer for discovering per-action fields and rules, but it does not directly clarify individual parameter meanings. This matches the baseline of 3 for high schema coverage.

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 'FRR BGP: peering state and neighbours' identifies the resource (FRR BGP) but lacks a verb; it reads like a label rather than a full statement of function. It does not explicitly say the tool can configure BGP or manage neighbors, which the action enum reveals. It is distinguishable from siblings like 'routing' by name, but the description itself is telegraphic.

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?

No alternatives or exclusion conditions are mentioned, and no sibling tools are referenced. The FRR-disabled caveat and the instruction to call action='help' provide operational context but do not tell an agent when to choose this tool over 'routing' or other siblings. Usage is implied by the resource name and scope rather than stated.

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