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

Beyond the annotations (readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false), the description discloses detailed behavioral traits: how event mode walks child markets, the threshold for partition deviations (>3pp), the Jaccard similarity anchor (≥0.30), placeholder filtering rules, and the fill-check mechanics with realizable_edge_pp. These enrich the agent's understanding without contradicting annotations.

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 description is dense and front-loaded with the core purpose, but it is a single long paragraph. While every sentence earns its place, the sheer length and lack of visual segmentation (e.g., bullet points) slightly reduce scannability. Still, it is efficiently worded and appropriately sized for the tool's complexity.

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?

Given there is no output schema, the description compensates by explaining the response structure ('opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context)') and the fill_check output, along with edge-case behaviors (e.g., null arb signal for >20% placeholders). The coverage of both modes, filters, and risk checks makes it fully contextually complete.

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?

Although schema coverage is 100%, the description adds significant meaning beyond the schema: it explains the no-args behavior, contrasts event vs topic modes in depth (e.g., 'walks child markets, checks date-axis / threshold-axis ordering'), and clarifies how the topic mode 'searches related events across the platform, flattens markets, runs the comparator on the union.' This goes far beyond the basic schema descriptions.

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 specific verb+resource+method: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' This clearly distinguishes the tool from siblings like polymarket_edges or polymarket_fill_risk, which focus on different aspects of Polymarket analysis.

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 description provides explicit mode instructions ('Call with NO args for a trending_scan', 'pass `event` for the strongest per-event partition_check', 'or `topic` for a themed cross-event scan') and names an alternative tool ('For custom sizing use polymarket_fill_risk'). It also warns when not to trade ('do not trade it'), offering clear decision guidance.

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