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

With no annotations, the description carries the full burden, and it does disclose a lot: the on-chain fields read, an ensemble plus red-team judging pass, verified quotes, and a deterministic code-only path for full-game sports markets where Gamma timestamps predate the window. What it never states is whether the tool merely advises or actually submits a dispute transaction, whether it is read-only, or what the response contains. Those omissions matter for a no-annotation tool whose name suggests disputing.

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 content is front-loaded and dense, with the trigger condition first and the judging method second, which is good structure. But it is a single run-on sentence that ends truncated ('before the g'), leaving an unfinished clause in the definition, and the parenthetical field list is packed in without separation. Efficiency is undermined by the abrupt cut-off.

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 six-parameter tool with nested objects and no output schema, the description explains the inputs and the judging process reasonably well. It never describes what a call returns — no mention of a verdict, an EV figure, a DISPUTE/ABSTAIN recommendation, or confidence — which is a real gap given there is no output schema to fall back on. The truncated final clause also leaves the deterministic-sports behavior incomplete.

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 83%, so the schema already explains market, prices, position, proposal overrides, and the tuning knobs like minEdgeUsd and otherDisputeProb. The description adds only indirect meaning by naming bond, finalFee and expiry as the live proposal fields being read and by implying evidenceUrls feed 'verified quotes'. It does not explain the economics parameters or how gasUsd, polUsd and aprOpportunity combine, so it sits at the baseline rather than above it.

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 names a concrete verb and resource: reads the live UMA proposal on Polygon (adapter, optimistic oracle, bond, finalFee, expiry) and judges the probability the proposal is wrong or too early. That is far more specific than the tool name 'dispute-ev' alone and is scoped to Polymarket markets inside the UMA challenge window. It does not, however, name any sibling or state how it differs from market-predictor or clarification-impact, and the text is cut off mid-sentence, which blunts the final scoping clause.

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?

The phrase 'For a Polymarket market inside its roughly two-hour UMA challenge window' gives a clear precondition for use, which is real guidance. There is no explicit when-not guidance, no mention of what to do outside the window, and no routing to an alternative tool for adjacent questions. Usage is therefore implied by scope rather than stated as a decision rule.

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