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

Beyond the annotations (readOnlyHint, openWorldHint=false, destructiveHint=false), it discloses the auth mechanism (X-Wever-Wallet-Proof bound to the exact JSON arguments and tool route), the price (0.10 USDC per call on Base via x402 exact), the free tier (10 signed-wallet calls per rolling 30 days), the POST endpoint, and that the return includes an Ed25519 signed receipt. It also reinforces the no-side-effects stance with an explicit list of what it will not do (no network fetch, money movement, messaging, or external write). That is materially more than the annotations convey.

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 is front-loaded, but the central sentence describing the report is a single unpunctuated run-on of well over a hundred words that requires re-reading to parse. The payment/legal boilerplate (endpoint, contract path, human page URL) is dense relative to the selection guidance it provides. Little is redundant, but the packaging is poor.

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?

There is no output schema, so the description must explain the return, and it does: what the report covers (agreed terms, room between limits, hard-limit collisions, soft conflicts, one-sided terms, unanswered issues) and the four verdicts. Combined with cost and auth disclosure, an agent has nearly everything needed to call it correctly; only the report's exact structure and the label/note parameters remain unaddressed.

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?

With schema coverage at 33%, the description has to carry weight and it does: it explains that `sides` holds exactly two sides, each with last-offer terms plus stated constraints carrying term, direction ('at most, at least or exactly'), value and a hard flag, and that open issues are included. It adds real semantics the schema does not, e.g. what a hard limit means for the analysis. It never mentions the optional `label` or the `note` field on open issues, so it is not complete.

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 opening states a specific action and resource ('submit a stalled negotiation') and the closing enumerates concrete verdicts (no_agreement_zone, agreement_blocked, room_unverified, room_to_agree), so an agent knows exactly what it gets. It also names three siblings and what each does better. The core action statement is buried inside a very long compound sentence, which keeps it from a clean 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?

It scopes usage to a 'stalled negotiation' and explicitly routes three alternative cases: wever_quote-compare for quotes on one job, wever_counterparty-brief for a counterparty brief, and wever_negotiation-counteroffer-check for a single counteroffer against a mandate. No explicit when-not condition or prerequisite ordering is given, so it falls just short of the top band.

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