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

Annotations already declare non-read-only, open-world, non-destructive. The description adds real behavioral context beyond that: the server verifies the signature against the exact payload it built, and the call blocks until the transaction is included in a block. That latency/blocking expectation is the key operational detail an agent needs; it does not cover timeout or failure/retry 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?

Two tightly packed sentences with zero filler, front-loading the action (broadcast) followed by the verification and blocking-return behavior. Every clause carries information.

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 usefully states what comes back (result plus decoded contract events) and the blocking wait. For a mutation tool with annotations covering the safety profile, this is nearly complete; it omits error/failure handling and any hint of typical wait duration.

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 both parameters are already documented as the intent_id from the write tool and the 0x-prefixed signature from sign_intent. The description reinforces the provenance of the signature (must match the exact built payload) but adds no format or constraint detail beyond the schema, so the baseline 3 applies.

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: broadcasts a prepared-and-signed transaction, and names the tools that produce its inputs (geode_* write tool, geode-local-signer sign_intent). It does not explicitly contrast with the sibling geode_get_intent, which is the natural alternative for checking intent status, so it stops short of full sibling differentiation.

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 clear context: use this after a write tool has built the payload and the local signer has signed the intent_id. The prerequisite chain is explicit, but there is no explicit when-not guidance (e.g., use geode_get_intent to poll instead of resubmitting).

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