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

Beyond the readOnly/destructive/idempotent annotations, the description discloses auth mechanics (Authorization: Bearer key passed to the MCP server), billing/quota behavior (counts against the key's plan), and an enforcement rule (signing/sending methods are refused). These are exactly the runtime traits an agent cannot infer from structured fields.

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?

Three tight sentences: purpose first, then auth/billing, then the safety limitation. No filler, and the most consequential constraint is stated explicitly rather than buried.

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 RPC tool with no output schema and full annotation coverage, the description covers identity, auth, billing, and the refusal boundary. It does not describe response shape or error behavior, but the free-form method/params nature makes that largely the upstream's concern.

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 coverage is 100% with each of the four properties documented inline, including chain slug examples and the archive-paid-plan note. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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 (Make a JSON-RPC call) and resource (any SwiftNodes chain) with the caller's API key, and the read-only restriction further narrows what it does. An agent can distinguish this from get_chain, probe_endpoint, and get_method_support without opening any schema.

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 operating context: the call is authenticated with the caller's key, is billed against that key's plan, and read-only methods that send or sign are refused. It does not explicitly compare against siblings like probe_endpoint or get_method_support, so the when-not guidance is implicit rather than named.

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