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

Annotations only declare destructiveHint/readOnlyHint/openWorldHint; the description goes well beyond them by disclosing that this writes to the chain, that nothing happens until the intent is signed and submitted, that the action is irreversible, and that it uses a two-call confirm_token handshake. These are exactly the behavioral traits an agent needs before invoking a destructive write.

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?

Four short sentences, front-loaded with the purpose before the mechanics. Every sentence carries distinct information (what it deletes, the intent model, the signer/submit chain, the confirmation flow) with no redundancy.

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, output-schema-less tool, the description covers the critical unknowns: irreversibility, the intent lifecycle, and the confirm_token return. The one gap is that the payload of the intent/preparation response beyond confirm_token is not described, though this is a minor omission given the two-stage design.

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 already 100%, so the baseline is 3. The description adds real value on top by explaining confirm_token's role in the flow ('the first call returns a confirm_token; call again with it to proceed'), clarifying that it is a second-call-only parameter rather than an upfront input.

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 with a specific verb+resource+scope: 'Delete all messages you sent to a group.' The scope words ('all', 'to a group', 'you sent') implicitly separate it from geode_messaging_delete_single_message_to_group and geode_messaging_delete_all_messages_to_account, but neither sibling is named, so an agent must infer the boundary rather than being told 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?

It gives a clear operating workflow: an intent is prepared for `signer`, then signed with geode-local-signer and submitted with geode_submit_intent. That is strong, actionable context. What is missing is explicit routing guidance for when to prefer this over the single-message or per-account delete variants in the same family.

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