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

Goes well beyond annotations (which say non-readonly, open-world, destructive): states writes to the chain, that it only prepares an unsigned intent for `signer`, that nothing happens before signing/submission, that it is irreversible, and that the first call returns a confirm_token needed for the second. Documents the two-phase safety behavior.

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 dense sentences with zero waste: action first, then write/signing flow, then the confirmation/irreversibility contract. Front-loaded and appropriately sized.

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 destructive, intent-preparing tool with no output schema, the description supplies everything needed to call it correctly: the signer requirement, external signing/submission pathway, irreversible nature, and confirm_token handshake.

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 baseline is 3; the description adds behavior for confirm_token (returned by first call, used to confirm irreversibility) and identifies signer as the account the transaction is prepared for, which is meaningful beyond schema text.

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 (Delete) and resource (every message in your paid inbox), clearly distinguishing it from sibling geode_messaging_get_my_paid_inbox (read) and other delete tools scoped to accounts/groups/lists.

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?

Explicitly describes the two-step flow: first call prepares the unsigned intent, sign with geode-local-signer, submit with geode_submit_intent; second call with confirm_token executes. The irreversible confirmation requirement is an explicit usage contract.

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