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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description goes well beyond them: it discloses that the call only prepares an unsigned intent, that nothing takes effect until signing and submission, that the action is irreversible, and that the first call returns a confirm_token needed for a second call. That is exactly the extra behavioral context an agent needs before touching 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?

Three tight sentences, front-loaded with actor and action, then the write/signing flow, then the irreversible two-step confirmation. No filler and no repetition; each sentence carries a distinct load.

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, open-world mutation with no output schema, the description covers everything material: what it does, that it writes to chain, that it is intent-based and requires signing/submission, and that it is gated by a confirm_token. Nothing an agent needs in order to call it correctly is missing.

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 the schema already explains signer, order_id, and confirm_token, and the description adds no new syntax, format, or constraint detail for them. It restates the signer role and the token round-trip, which is helpful framing but redundant with the structured fields, so 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 (deny), the exact resource (a buyer's problem report on an order), and the acting role (Seller), which is enough to separate it from sibling resolution tools like geode_market_issue_refund or geode_market_issue_replacement without opening a schema. An agent can tell at a glance that this rejects a claim rather than granting one.

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 clear context for use (seller responding to a buyer problem report) and spells out the required follow-through workflow: sign with geode-local-signer and submit with geode_submit_intent. What it omits is any explicit exclusion or alternative, e.g. which sibling to call instead when the seller wants to accept or refund the claim.

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