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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds substantial behavioral context beyond those: unclassified legs are never paired, temporal_alignment null does not mean aligned, compatibility codes are enumerated, fees are gross because Kalshi fees are not modeled, and skipped comparison counters are exposed. This is exactly the kind of non-obvious behavior an agent needs to know before trusting the output.

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 long, but it is organized with clear labels like TWO MODES, RESPONSE, and SAFETY FIELDS, and the core purpose is front-loaded. Most sentences carry needed information given the absence of an output schema, though there is some repetition around identical matcher behavior and mode symmetry that keeps it from being maximally tight.

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 full burden of explaining return values, and it does so thoroughly: raw probabilities, top_spreads_pp sign convention, per-entry flags, temporal_alignment null semantics, skipped_* counters, fees_note, and compatibility codes are all covered. An agent has enough information to call the tool and interpret its results correctly.

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?

Input schema coverage is 100%, so the baseline is already strong. The description adds valuable interaction semantics beyond the schema: the explicit ticker and slug override their topic-mapped side, both modes run the same matcher, and the topic list is spelled out with concrete shortcut names. This meaningfully clarifies how the parameters combine.

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 resource and function: it reports the cross-venue spread between Kalshi and Polymarket for the same resolving question, and goes on to specify two input modes and the response shape. However, it never explicitly contrasts itself with sibling tools such as polymarket_arbitrage, so it stops short of full sibling differentiation.

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 two modes are clearly explained: topic shortcuts auto-fetch matching events, while explicit kalshi_event_ticker + polymarket_event_slug are for custom pairings, and the description notes that both modes run the identical matcher. It also warns that pre-mapped topics are not automatically tradeable and that safety fields should be read even when pairs are returned, though it does not mention when to prefer a sibling tool for arbitrage.

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