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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real behavior the annotations cannot: a refused method is never sent, probing asks the node and yields yes/no/restricted/unknown, and the catalogue is shape guidance rather than an authoritative coverage list. This is meaningful disclosure beyond the 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?

The core purpose and the rpcCall relationship are front-loaded in the first sentence, and each subsequent sentence carries distinct information (probing semantics, refusal behavior, catalogue caveat). It is dense — two ideas are packed into the probe sentence — but nothing is wasted.

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?

There is no output schema, so the description must carry the return-value burden, and it does: positional param shape, a worked example per method, rpcCall's verdict, and the served value set. Combined with the catalogue caveat, an agent has everything needed to invoke and interpret results correctly.

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%, so the baseline is 3, but the description adds value the schema does not: probe requires an explicit methods list, the list is capped at 12, and served reflects the caller's key, tenant and the chain's blockchain schema with the discrete outcomes named. The methods param's dual role (probe target vs. catalogue omission) is clarified.

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 and resource — describes what a JSON-RPC method takes and whether the key can call it — and clearly distinguishes itself from the sibling rpcCall by returning rpcCall's own verdict rather than executing it. An agent can tell these two apart without opening either 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?

Gives a clear conditional for probing ('Pass probe:true with an explicit methods list ... to also ask the node') and states the fallback behavior when methods is omitted. It ties itself to rpcCall but never says explicitly 'call this before rpcCall to check permission,' so the primary workflow trigger is implied rather than stated.

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