Give your side of a dispute

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

Annotations already mark this as a non-destructive write, so the description's job is to add context — and it does: one-shot semantics, a race condition (first response wins on delivery_failed), the pre-decision window, and an auth requirement (GLONGUS_API_KEY). It omits what happens to the response afterward (whether it binds the outcome) and any length/content expectations.

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 tight sentences, with the eligibility rule front-loaded ahead of the exception and the auth note. Dense but every clause carries a distinct rule; nothing is filler.

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 two-parameter mutation with no output schema this covers eligibility, limits and credentials well, but leaves two gaps an agent needs: what to put in the response body and what the call changes about dispute state. Adequate, not complete.

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 0% on two parameters, so the description carries the full burden and does not meet it. It never explains what the `response` string should contain, whether it is visible to the counterparty, or that `transaction_id` must be the disputed transaction.

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?

Names a specific verb (respond) and resource (dispute) plus the exact eligibility rule: the party who did not raise the dispute, one response only. That scope statement separates it from propose_dispute_split and decide_dispute_proposal without naming them, though an explicit sibling reference would push it to a 5.

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 timing (before anything is decided), a frequency limit (once), and an exception path for Glongus-raised delivery_failed disputes where either side may respond. It stops short of saying what the alternative routes are when you cannot respond — e.g. proposing a split.

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