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

Annotations only supply readOnlyHint/openWorldHint, and the description goes well beyond them by disclosing the stake deposit, the matching bond requirement and the 24h dispute window. It does not disclose that a wallet signature and gas are needed or that the output is a set of calls to sign, which matters for an agent chaining build steps.

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 with the precondition front-loaded ('After trading:') and one parenthetical per action; every clause contributes an actor, a timing rule, or a bond/stake requirement.

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 an action-multiplexer over five settlement paths with four parameters, the definition covers who may invoke each action and under what precondition, which is the main ambiguity. It stops short of describing the built output or any post-call steps, a minor gap given there is no output schema.

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 most parameters already carry their own descriptions and the enum values define the actions. The description adds intent per action value (who may call it and when) but says nothing further about `id`, `wallet` or `outcome` beyond what the schema states ('required for propose').

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 enumerates the five resolution actions (propose, dispute, finalize, redeem, withdraw_liquidity) and scopes them 'after trading', which pairs with the title 'resolve or settle a prediction market' to make the purpose concrete. It never states outright that the tool builds unsigned calls rather than submitting them, leaving the 'build' aspect to the title and the wallet parameter text.

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?

Each action carries explicit actor and timing conditions: dispute is 'anyone but the solver... during the 24h window', finalize is 'anyone, once the window passes', redeem is 'holders, after settlement'. The when-not is only implicit in 'After trading'; no sibling alternative (e.g. build_prediction_trade, quote_prediction_trade) is named as a routing alternative.

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