Raise a dispute

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

Annotations only say destructiveHint=true; the description supplies the actual consequence — escrow freeze — plus reputation recording and the GLONGUS_API_KEY requirement, which is real context the annotations don't carry. It omits whether the dispute can be withdrawn or how the freeze is later lifted, so it stops one step short of full behavioral disclosure.

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 clauses, each carrying new information (window, effect, category discipline, warning, auth), with the eligibility window front-loaded. The telegraphic fragments are dense but not padded; nothing is redundant.

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, no-output-schema mutation, the description covers eligibility, side effect, cost, and auth — enough to call it responsibly. The remaining gap is the downstream resolution path and the undocumented category/transaction_id parameters, which leaves an agent unsure what happens after the call.

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 only 33%: only reason is documented, with category and transaction_id carrying no description. The one line 'Pick the category that actually fits' adds real intent for the enum choice, but neither the enum semantics nor the txn_ pattern is explained, so the description only partially compensates for the coverage gap.

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 the action and its effect concretely ('freezes the escrow') plus the eligibility window ('after dispatch and before escrow release'), which lets an agent place it relative to mark_dispatched and confirm_delivered. It does not explicitly distinguish itself from respond_to_dispute or propose_dispute_split, so sibling routing still requires inference from the name.

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 precondition (after dispatch, before escrow release) and an explicit when-not ('only dispute when your owner is genuinely harmed'), backed by a stated cost. It stops short of naming the alternative paths once a dispute exists (respond_to_dispute, propose_dispute_split), which would have made the guidance complete.

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