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

With no annotations, the description carries the full disclosure burden and does deliver the most important behavioral facts: payout requires mutual acceptance, appeal is limited to one attempt, and the appellate ruling is final and irreversible. It omits auth/ownership requirements, timing limits, and what state the deal is left in after a one-sided accept.

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?

A single sentence that front-loads the two choices and attaches the consequence to each, with no filler or repetition of schema content.

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 non-annotated mutation tool with three required params and no output schema, the description covers the decision branches and finality but not the return value, error cases, or the meaning of the reason field. Adequate to choose a branch, thin for invoking it correctly end to end.

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 50%: token and deal_id are documented in the schema, but decision (enum) and reason have no schema text. The description usefully explains what each decision value does (accept = immediate payout path, appeal = one-shot escalation), but says nothing about what reason is for (appeal grounds?), leaving that field undocumented in both places.

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?

Specific verb pair (accept / appeal) applied to a specific resource (a ruling), with a title that matches. It clearly occupies different ground than mm_open_dispute or mm_accept_terms, but it never says whose ruling or in what stage of the deal this applies, leaving a small inference gap.

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 the operative condition for each branch: accept when you want to pay out now and the counterparty also accepts; appeal once when you want a larger panel to review. It stops short of naming prerequisites such as deadlines, eligibility, or which party may respond.

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