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

Goes beyond the annotations (which already declare readOnly/idempotent/non-destructive) by disclosing key behavioral traits: it never touches a private key, re-derives and re-checks the proof before emitting, and reads the live price() so a bad nonce fails locally. These are genuinely useful failure-mode and safety disclosures not present in 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?

Front-loads the core action and output shape, then layers safety and failure behavior. Dense but every clause carries information; 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?

With no output schema, the description correctly compensates by describing the emitted payload ({to, data, value} plus wallet commands) and the failure behavior. Complete enough for an agent to call it, though the exact command/response format remains unstated.

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 nonce, minter, and slippageBps are all documented in the schema itself. The description only glancingly references the live price() read; the 200bps buffer/auto-refund semantics are already in the schema, so there's little added meaning.

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 ('builds a ready-to-broadcast mint transaction from a mined nonce') and enumerates the exact artifact produced ({to, data, value} plus copy-paste wallet commands). This clearly separates it from nonce_mine (produces the nonce) and nonce_verify (checks it).

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 phrase 'from a mined nonce' and 'a bad nonce fails here instead of costing gas on a revert' imply this is the pre-broadcast step after mining, giving implicit sequencing. But it never explicitly says 'use after nonce_mine' or names when NOT to use it, so usage is inferred rather than directed.

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