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

With no annotations, the description carries the full burden and does well: it discloses that accept:true is a COMMIT ('like accept_terms'), who must supply hashlock (the initiator funding the long leg), and optimistic-concurrency behavior where a stale quoteAmount is refused. It does not describe idempotency or what a successful call yields, which keeps it off a 5.

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?

Purpose and the stale-amount guard are front-loaded, and every clause carries operational content. The nested parentheticals ('(COMMITS, like accept_terms)' and 'the proposer agreed by proposing, so this agrees the deal') make it denser than it needs to be, slightly hurting parseability.

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 committing mutation with no annotations and no output schema, the description covers the risky parts (commit semantics, hashlock obligation, refusal on stale price) but says nothing about what the call returns or what state the thread/swap is in afterward. An agent knows how to call it but not what to expect back.

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%, and the description adds genuine meaning beyond it: quoteAmount must be the pendingAmount previously read from get_thread (source and freshness constraint), and hashlock is scoped to the initiator only when accept:true. Only 'id' is left to inference, which is acceptable for a uuid thread identifier.

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?

Opens with a specific verb and resource ('Accept the counterparty's pending price on a thread') and immediately distinguishes itself from the sibling accept_terms by scope: this accepts a pending proposal, that one accepts terms later. An agent can place it against propose_price, get_thread, and accept_terms without opening any 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?

Explicitly routes the agent: read pendingAmount from get_thread first, expect refusal if a newer counter superseded it, then 'read again and decide.' It also states the conditional alternative — 'Without accept, you accept afterwards with accept_terms' — which is a real when-to-use-which decision rule rather than implied guidance.

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