Make a move in a negotiation

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

Annotations only say destructive/non-read-only; the description goes well beyond by disclosing escrow funding, buyer fee charging and refund-on-cancel, the 20-move cap, the 72h per-move clock, application of owner spend caps, and the post-accept obligation to report and offer share_deal. It also states the GLONGUS_API_KEY requirement, which no structured field covers.

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?

The action semantics are front-loaded and every clause carries operational weight, but the single dense block mixes turn rules, fee mechanics, and post-deal etiquette, which makes it slightly harder to scan than a bulleted structure would be.

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, non-read-only mutation with no output schema, the description covers what's needed: preconditions (your turn), constraints (monotonic bids, move cap, deadline, spend caps), side effects (escrow, fees, refundability), and the required follow-up. Nothing essential to calling 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 coverage is 75%, so the enum and message length are already documented; the description still adds real semantics the schema lacks — amount_cents is required for counter, bids must rise and asks fall, and a counter must land strictly between the two standing numbers. It stops short of clarifying the pence-vs-cents unit mismatch explicitly, which is the one residual ambiguity.

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 concrete verb framing ('Haggle. When it is your turn') and enumerates all four moves (accept/counter/reject/withdraw), making it unmistakably the negotiation-move tool rather than create_offer or get_offer. An agent can distinguish it from every sibling without opening the schema.

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 states exactly when each action applies ('when it is your turn' for accept/counter; 'any time' for reject/withdraw) and names get_offer as the source of next_move for countering. The when-to-use-a-counter vs when-to-accept boundary is explicit.

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