kiwi_rpc

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

With no annotations provided, the description carries the behavioral disclosure burden. It explicitly says 'Unguarded' and that the caller is responsible for correct method and params, signaling that this tool can perform arbitrary, potentially destructive RPC calls. It also explains the positional param convention and links to the full API list, though it does not cover auth, rate limits, or error/return behavior.

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: it states the purpose first, then param semantics, then the safety warning, and ends with the reference URL. Every sentence contributes meaningful guidance with no 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 generic passthrough tool, the description is largely complete: method syntax, param shape, examples, risk warning, and canonical documentation link are all present. It could be slightly stronger by explicitly advising agents to prefer specialized sibling tools for covered methods or by noting that return values vary by method, but the documentation URL mitigates these gaps.

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 already documents both parameters with 100% coverage. The description adds valuable meaning beyond the schema: concrete method examples and the positional-array convention, including typical shapes for *.filter and *.update calls. This helps an agent construct params correctly.

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's action: 'Call ANY Kiwi JSON-RPC method directly.' It includes concrete method examples and contrasts with the specialized sibling tools by emphasizing direct, unguarded access to the full RPC API. An agent can immediately understand this is a generic passthrough/fallback tool.

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 gives clear context for when this tool is appropriate: any Kiwi JSON-RPC method, especially those not covered by dedicated wrappers. It warns the caller to be responsible and points to the full method documentation. It does not explicitly state 'prefer a sibling tool when one exists,' but the generic-purpose framing makes the intended use clear.

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