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

Annotations already flag destructive/openWorld/not-readOnly, but the description adds substantially more: irreversible, keep-alive so the account can never be emptied below minimum balance, two-phase confirmation with a confirm_token, account creation on send to a new address, and rate-cap exposure.

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?

Purpose is front-loaded and every clause carries operational meaning; there is little filler. The single dense paragraph packs the two-step flow, signing step, and caps into one wall of text, which slightly hurts scanability.

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 explains what the first call returns (confirm_token and real cost) and what to do next, plus constraints. It does not cover confirm_token expiry or mismatch behavior, which matters for an irreversible transfer, but the core flow is adequately documented.

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 schema already documents signer, dest, amount, and confirm_token; the description adds lifecycle context for confirm_token (returned by first call, reused on second). However, it introduces '`expect`' — a field of geode-local-signer, not of this tool's schema — which could mislead an agent into passing an unsupported parameter.

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 precise verb+resource: 'Send GEODE from `signer` to another account', and immediately qualifies it with keep-alive semantics. It is clearly distinguishable from siblings such as geode_submit_intent, which it names as the final step rather than a competitor.

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?

Lays out the exact operating procedure: first call returns confirm_token and real cost, second call retrieves the intent, sign with geode-local-signer, then submit with geode_submit_intent. It also states the new-address minimum (1 GEODE) and that this counts toward per-transaction and 24-hour caps.

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