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

Annotations already declare readOnlyHint, idempotentHint, and closed-world, and the description is consistent with them, reinforcing 'Prepared, not executed'. Beyond the annotations it adds genuinely useful behavioral context: the wallet signs and sends, and 'the meter never sees a key' discloses the key-handling posture. It does not cover failure behavior for an invalid action string.

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?

Very compact, with the core identity front-loaded in the first fragment and each subsequent clause mapping to a distinct mode. The telegraphic fragment style ('No action: every action and its params') is dense to the point of being cryptic, but no sentence 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?

With only two params, a freeform args object, and no output schema, the description covers how to call the tool in each mode but says nothing about the shape of the returned calldata or what happens on an invalid action. It tells the agent how to discover valid actions (call with no action), which partly compensates. Adequate but with clear remaining 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?

Schema coverage is 0% and 'args' is a freeform object, so the description carries the full burden — and it largely does, giving action format examples ('notary/notarize', 'swap/exact_in'), the special action='sign' value, and the meaning of args as transactions plus preconditions. The open-ended arg shapes per action remain undisclosed except by example.

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 opens by naming the resource concretely — 'unsigned calldata for on-chain actions' — so an agent knows this builds transaction payloads rather than executing them. It also carves out the 'sign' mode as a distinct branch. It does not differentiate from plausible siblings like trade, play, or wire, which keeps it below a 5.

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?

It gives explicit mode-based guidance: omit 'action' to enumerate every action and its params, pass action+args to prepare a transaction, and action='sign' for off-chain game texts. That is real when-to-use routing. It still offers no comparison against sibling tools, so the agent has no rule for choosing this over trade or play.

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