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

Annotations cover the safety profile (readOnly, openWorld, non-destructive), and the description adds substantial behavior beyond them: the exact signal vocabulary (WATCH/ARB), the fields returned (gap in pp, cheaper venue, settlement_match), and a tier gate — free returns only the top 3 gaps while Pro returns the full board. That tiering and settlement-comparison context is exactly what an agent needs to interpret results.

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?

Front-loads the use case in the first sentence, then lists the returned quantities compactly, and closes with the free/Pro distinction. Slightly dense with quoted trigger phrases and jargon, but every clause carries information and nothing is redundant.

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?

With no output schema, the description carries the return-value burden and does so: it enumerates the output fields and the free/Pro result-set sizes. For a one-optional-parameter read tool, an agent has everything needed to call it and interpret the response.

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 100% and minGap's accepted formats (number or "3pp"/"3%") and default/WATCH-threshold meaning are already documented in the schema. The description mentions the WATCH/ARB signal and "top 3 gaps" but adds no new syntax or filtering semantics beyond what the schema provides, so the baseline 3 applies.

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?

States a specific verb+resource — cross-venue arbitrage gaps on the same sports contract between Kalshi and Polymarket — and names the concrete deliverables (gap in pp, WATCH/ARB signal, cheaper venue, settlement_match). This is clearly separable from siblings like ladder_arb, combo_edge, or scan_mispricings, which cover different products or strategies.

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?

Gives explicit user-phrasing triggers ("where is the arbitrage", "Kalshi vs Polymarket price gaps") that map well to intent, plus a free-vs-Pro condition. It does not name an alternative tool or state when not to use it, so the routing guidance stops short of full 5-level specificity.

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