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

Annotations already cover the safety profile (readOnlyHint, openWorldHint), yet the description adds real context: free board, no key required, what the three signal classes mean, what each row contains, and that fleet/size detail is gated behind Pro. It omits rate limits, pagination behavior and data freshness beyond a single dated measurement.

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-loaded purpose followed by return contents, pricing/measurement context, and trigger phrases, all in a compact block. The Sept 2026 stat and the Pro upsell are slightly promotional but still informative; the trailing keyword list earns its place for retrieval.

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?

No output schema exists, so the description carries the burden and does describe the return shape (both tickers, both books, gross edge in cents, volume, kickoff, tier). What it leaves unstated is freshness/latency of the scan and result ordering/truncation behavior for the limit parameter.

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 100%, so limit/sport/signal/min_edge/min_volume are already documented in the schema. The description hints at 'net-of-fee edge' and row substance but adds no syntax or default guidance beyond what the schema supplies — baseline 3.

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?

Specific verb + resource + mechanism: 'Scan Kalshi college football and NFL spread/total ladders for internal price inconsistencies.' It even defines the signal condition (strikes priced out of order on the same side of the same game), which separates it from generic siblings like find_arbitrage or nfl_ladder.

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?

Provides concrete trigger phrasings ('is any CFB ladder mispriced', 'where can I make a market on Kalshi today') and states when it applies, but never names an alternative sibling (find_arbitrage, nfl_ladder, scan_mispricings) or states when NOT to use it, so routing between the several arb/edge tools is left partly to inference.

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